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 | 53082 |
Below is a question asked on the forum security.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I use bcrypt (32 rounds) and once the hash is produced, I get the sha512 of that hash and I then hash that with blow fish and once that is done, I hash it again with sha512 with a salt that has been hashed with bcrypt (94 rounds) that is 33 characters long to each user password. So is that secure or not?
Now provide the response and nothing else.
| Yes but everything after the first bcrypt is completely unnecessary. bcrypt automatically generates and appends a salt as well (in the ruby implementation anyway), and changing the number of rounds is sufficient to ensure that the hashing scheme is slow enough to deter offline brute forcing. | {} | {'log_upvote_score': 4, 'links': ['https://security.stackexchange.com/questions/53082', 'https://security.stackexchange.com', 'https://security.stackexchange.com/users/31381/']} | jdg_382541 |
stackexchange | llm_judgeable_groundtruth_similarity | 32277992 |
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 webdriver(java) for a unique test where a page reloads itself when you log on, I've been unable to wait for the element to load because it is already there before the reload. So far the only way I've been able to get it to work is to use a thread.sleep, is there a way to listen for a page refresh?
Now provide the response and nothing else.
| One way to solve this is, to get a reference to the element you need, that appears both on the login-page and the reloaded page.Then you can use the ExpectedConditions.stalenessOf to occur, and then you can be sure, that the element is removed from the DOM and a new element is created. Well, the last part is not guaranteed by this method, but at least you know that the old element is gone. The code could look something like this: WebElement elementOldPage = driver.findElement(By.id("yourid"));... do login etc ...WebDriverWait wait = new WebDriverWait(driver, 10);wait.until(ExpectedConditions.stalenessOf(elementOldPage));WebElement elementNewPage = driver.findElement(By.id("yourid")); | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/32277992', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/5278162/']} | jdg_382542 |
stackexchange | llm_judgeable_groundtruth_similarity | 358113 |
Below is a question asked on the forum mathoverflow.net. Provide a good and informational response to it like a helpful human would.
Question:
A. Okounkov said, "symplectic resolutions are Lie algebras of the 21st century." Is there a conjecture on the classification of symplectic resolutions? Do Braverman-Finkelberg-Nakajima Coulomb branches give most known examples of symplectic singularities (and do BFN Coulomb branches have explicit descriptions)? Where can one find a list of all known examples of symplectic resolutions? What are the consequences of the classification of symplectic resolutions in representation theory etc.? Is classification of symplectic resolutions a very hard problem (or, if it is intractable, is there a nice class of symplectic resolutions analogous to semisimple Lie algebras that can be classified)? What are some directions in this problem that can be approachable (cf. results of Bellamy-Schedler)? Also, is there an object "Lie group of the 21st century" which fits into an analogy [Lie group of the 21st century] : [symplectic resolution (Lie algebra of the 21st century)] = Lie group : Lie algebra (I suppose quantizations of symplectic resolutions loosely correspond to universal enveloping algebras in this analogy)?
Now provide the response and nothing else.
| Here is an answer by Gwyn Bellamy, which he let me post here: 1) Is there a conjecture on the classification of symplectic resolutions? No, not that I am aware of. I think this is the wrong question anyway. Rather, one should first try to classify all conic symplectic singularities. There is an amazing result of Namikawa that says that if you bound the degrees of your algebra of functions on the singularity then there are only countably many isomorphism classes. So it is not inconceivable that a classification is possible. I believe that Namkiawa is trying to develop such a classification program. See in particular the papers of his PhD student T. Nagaoka. I think if we had such a classification then it would be relatively straightforward to decide when they admit symplectic resolutions. 2) Do Braverman-Finkelberg-Nakajima Coulomb branches give most known examples of symplectic singularities? Maybe. First, it is not known how many of these are actually conic (to fit into (1)). If we consider first the Higgs branch rather than the Coulomb branch then I think it is a reasonable question to ask if most conic symplectic singularities can be realised as Hamiltonian reductions of a symplectic vector space with respect to a (possibly disconnected) reductive group. One gets all nilpotent orbit closures of classical type this way for instance (I don’t know if this is still true for more general Slodowy slices). Now if this is the case and we believe symplectic duality then one should also realise most conic symplectic singularities as coulomb branches. I think there’s a slight issue here though. The definition as given by BFN does not work so well for disconnected groups. For instance if we take the gauge group to finite then the coulomb branch is just a point. Another way to see that one probably can’t get many quotient singularities (V/G for G \subset Sp(V) finite) is that the coulomb branch is always rational (has same field of fractions as affine space). I don’t think V/G is always rational even for type E Kleinian singularities, so can’t be realised via BFN construction. Maybe there is a way to modify their construction. 3) Do BFN Coulomb branches have explicit descriptions? No (though I am not an expert) outside the quivers gauge theories of finite type (or affine type A) there is no geometric or moduli description. 4) The case of quotient singularities is the one I am most familiar with (work with Travis). Here the classification of symplectic resolutions is almost complete, except for a finite number of exceptional groups. I believe that a PhD student of U. Thiel is looking at these. We also know precisely when quiver varieties admit symplectic resolutions, and I believe there is a classification due to Fu/Namikawa for (normalizations of) nilpotent orbit closures. 5) Also, is there an object "Lie group of the 21st century" which fits into an analogy [Lie group of the 21st century] : [symplectic resolution (Lie algebra of the 21st century)] = Lie group : Lie algebra? Yes, I would say this picture is very well understood. See the Asterique article by Braden-Licata-Proudfoot-Webster and subsequent work by Losev. | {} | {'log_upvote_score': 4, 'links': ['https://mathoverflow.net/questions/358113', 'https://mathoverflow.net', 'https://mathoverflow.net/users/12395/']} | jdg_382543 |
stackexchange | llm_judgeable_groundtruth_similarity | 512412 |
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:
Determine whether or not $((P\land Q)\implies R)$ tautologically implies $((P\implies R)\lor (Q\implies R))$ How do I determine that $((P\land Q)\implies R)$ tautologically implies $((P\implies R)\lor(Q\implies R))$? The problem is not to show equivalence, but to determine whether one formula tautologically implies another, and I'm confused about the difference. Any clarification would be appreciated.
Now provide the response and nothing else.
| A formula A either will tautologically imply another formula B, or it will not do so. If A does NOT tautologically imply B, then there exists some truth-value assignment such that A holds true, and B qualifies as false. Suppose ((P→R)∨(Q→R)) false. Then, (P→R)qualifies as a false, and so does (Q→R). Thus, P qualifies as true, Q qualifies as true, and R qualifies as false. If those conditions hold, then ((P∧Q)→R) qualifies as false also. So, it is not the case that A does not tautologically imply B. Thus, because of the content of the initial sentence, ((P∧Q)→R) tautologically implies ((P→R)∨(Q→R)). | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/512412', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/88678/']} | jdg_382544 |
stackexchange | llm_judgeable_groundtruth_similarity | 594604 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
String s1 = "BloodParrot is the man"; String s2 = "BloodParrot is the man"; String s3 = new String("BloodParrot is the man"); System.out.println(s1.equals(s2));System.out.println(s1 == s2);System.out.println(s1 == s3);System.out.println(s1.equals(s3)); // output true true false true Why don't all the strings have the same location in memory if all three have the same contents?
Now provide the response and nothing else.
| Java only automatically interns String literals . New String objects (created using the new keyword) are not interned by default. You can use the String.intern() method to intern an existing String object. Calling intern will check the existing String pool for a matching object and return it if one exists or add it if there was no match. If you add the line s3 = s3.intern(); to your code right after you create s3 , you'll see the difference in your output. See some more examples and a more detailed explanation . This of course brings up the very important topic of when to use == and when to use the equals method in Java. You almost always want to use equals when dealing with object references. The == operator compares reference values, which is almost never what you mean to compare. Knowing the difference helps you decide when it's appropriate to use == or equals . | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/594604', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/68653/']} | jdg_382545 |
stackexchange | llm_judgeable_groundtruth_similarity | 35724423 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
The following code compiles cleanly with GCC: void func(int arg1, decltype(arg1) arg2){ (void)arg2;}int main(){} I used this command to compile: g++ -std=c++14 test.cpp -o test -pedantic-errors -Wall -Wextra But such usage of a parameter in the middle of function declaration seems weird. Is it actually valid in standard C++, or is it a GCC extension?
Now provide the response and nothing else.
| This is fine. The ISO C++11 Standard even gives your situation as an example. First the parameter is in scope: 3.3.3 Block scope [ basic.scope.local ] 2 The potential scope of a function parameter name (including one appearing in a lambda-declarator) or of a function-local predefined variable in a function definition (8.4) begins at its point of declaration. An example can be found here: 8.3.5 Functions [ dcl.fct ] 5 [ Note: This transformation does not affect the types of the parameters. For example, int(*)(const int p, decltype(p)*) and int(*)(int, const int*) are identical types. — end note ] | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/35724423', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/673852/']} | jdg_382546 |
stackexchange | llm_judgeable_groundtruth_similarity | 15125457 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
The problem When I'm working with libraries that support type-level programming, I often find myself writing comments like the following (from an example presented by Paul Snively at Strange Loop 2012 ): // But these invalid sequences don't compile:// isValid(_3 :: _1 :: _5 :: _8 :: _8 :: _2 :: _8 :: _6 :: _5 :: HNil)// isValid(_3 :: _4 :: _5 :: _8 :: _8 :: _2 :: _8 :: _6 :: HNil) Or this, from an example in the Shapeless repository: /** * If we wanted to confirm that the list uniquely contains `Foo` or any * subtype of `Foo`, we could first use `unifySubtypes` to upcast any * subtypes of `Foo` in the list to `Foo`. * * The following would not compile, for example: */ //stuff.unifySubtypes[Foo].unique[Foo] This is a very rough way of indicating some fact about the behavior of these methods, and we could imagine wanting to make these assertions more formal—for unit or regression testing, etc. To give a concrete example of why this might be useful in the context of a library like Shapeless, a few days ago I wrote the following as a quick first attempt at an answer to this question : import shapeless._implicit class Uniqueable[L <: HList](l: L) { def unique[A](implicit ev: FilterAux[L, A, A :: HNil]) = ev(l).head} Where the intention is that this will compile: ('a' :: 'b :: HNil).unique[Char] While this will not: ('a' :: 'b' :: HNil).unique[Char] I was surprised to find that this implementation of a type-level unique for HList didn't work, because Shapeless would happily find a FilterAux instance in the latter case. In other words, the following would compile, even though you'd probably expect it not to: implicitly[FilterAux[Char :: Char :: HNil, Char, Char :: HNil]] In this case, what I was seeing was a bug —or at least something bug-ish—and it has since been fixed . More generally, we can imagine wanting to check the kind of invariant that was implicit in my expectations about how FilterAux should work with something like a unit test—as weird as it may sound to be talking about testing type-level code like this, with all the recent debates about the relative merit of types vs. tests. My question The problem is that I don't know of any kind of testing framework (for any platform) that allows the programmer to assert that something must not compile . One approach that I can imagine for the FilterAux case would be to use the old implicit-argument-with-null-default trick : def assertNoInstanceOf[T](implicit instance: T = null) = assert(instance == null) Which would let you write the following in your unit test: assertNoInstanceOf[FilterAux[Char :: Char :: HNil, Char, Char :: HNil]] The following would be a heck of a lot more convenient and expressive, though: assertDoesntCompile(('a' :: 'b' :: HNil).unique[Char]) I want this. My question is whether anyone knows of any testing library or framework that supports anything remotely like it—ideally for Scala, but I'll settle for anything.
Now provide the response and nothing else.
| Not a framework, but Jorge Ortiz ( @JorgeO ) mentioned some utilities he added to the tests for Foursquare's Rogue library at NEScala in 2012 which support tests for non-compilation: you can find examples here . I've been meaning to add something like this to shapeless for quite a while. More recently, Roland Kuhn ( @rolandkuhn ) has added a similar mechanism, this time using Scala 2.10's runtime compilation, to the tests for Akka typed channels . These are both dynamic tests of course: they fail at (test) runtime if something that shouldn't compile does. Untyped macros might provide a static option: ie. a macro could accept an untyped tree, type check it and throw a type error if it succeeds). This might be something to experiment with on the macro-paradise branch of shapeless. But not a solution for 2.10.0 or earlier, obviously. Update Since answering the question, another approach, due to Stefan Zeiger ( @StefanZeiger ), has surfaced . This one is interesting because, like the untyped macro one alluded to above, it is a compile time rather than (test) runtime check, however it is also compatible with Scala 2.10.x. As such I think it is preferable to Roland's approach. I've now added implementations to shapeless for 2.9.x using Jorge's approach , for 2.10.x using Stefan's approach and for macro paradise using the untyped macro approach . Examples of the corresponding tests can be found here for 2.9.x , here for 2.10.x and here for macro paradise . The untyped macro tests are the cleanest, but Stefan's 2.10.x compatible approach is a close second. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/15125457', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/334519/']} | jdg_382547 |
stackexchange | llm_judgeable_groundtruth_similarity | 111455 |
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 some old scripts that I try to update. Some of the code condenses to: export X=`(echo "abc"; echo "def")` echo $X which gives the expected output: abc def Now the internet tells me backticks are out $() is what I need to use, but when I try: export X=$((echo "abc"; echo "def")) X is not set and I get the error: bash: echo "abc"; echo "def": syntax error: invalid arithmetic operator (error token is ""abc"; echo "def"") What am I doing wrong?
Now provide the response and nothing else.
| The $(( … )) syntax is an arithmetic expression . What is missing is a space between the $( and the following ( , to avoid the arithmetic expression syntax. The section on command substitution in the shell command language specification actually warns for that: If the command substitution consists of a single subshell, such as: $( (command) )a conforming application shall separate the "`$(`" and '`(`' into two tokens(that is, separate them with white space). This is required to avoid anyambiguities with arithmetic expansion. | {} | {'log_upvote_score': 6, 'links': ['https://unix.stackexchange.com/questions/111455', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/58003/']} | jdg_382548 |
stackexchange | llm_judgeable_groundtruth_similarity | 54254553 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Hello everyone I have been trying dynamic imports in react for rendering my components for an app created with CRA (create-react-app) and while it works perfectly for some cases but for some it returns a cannot load module error for instance I loaded a component(placed in a directory under src) dynamically in my index.js which works fine but when I try to render a child or nested component inside that also with a dynamic import approach it gives error cannot load module. Note this error occurs only if the nested component is placed outside the directory of the original parent component enough talk here is the code. My index.js placed under src. import React, { Component } from 'react'; import ReactDOM from 'react-dom'; import './index.css'; class Dynamic extends Component { constructor(props) { super(props); this.state = { module: null }; } componentDidMount() { console.log('in comp mount') //alert("in comp mount") const { path } = this.props; import(`${path}`) .then(module => this.setState({ module: module.default })) } render() { console.log('in render') // alert("in render") const { module: Component } = this.state; // Assigning to new variable names @see: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Operators/Destructuring_assignment return( <div> {Component && <Component path= '../FooterComp/Footer' />} </div> ) } }ReactDOM.render(<Dynamic path='./Components/FirstComponent' />, document.getElementById('root')); FirstComponent.js placed in Components directory under src. import React, { Component } from 'react';import logo from '../logo.svg';import '../FirstApp.css';class App extends Component { constructor(props) { super(props); this.state = { module: null }; } componentDidMount() { console.log('in comp mount') //alert("in comp mount") const { path } = this.props; alert(path) import(`${path}`) .then(module => this.setState({ module: module.default })) } render() { const { module: Component } = this.state; return ( <div className="App"> <header className="App-header"> <img src={logo} className="App-logo" alt="logo" /> <p> Edit <code>src/App.js</code> and save to reload. </p> <a className="App-link" href="https://reactjs.org" target="_blank" rel="noopener noreferrer" > Learn React </a> </header> {Component && <Component />} </div> ); }}export default App; Footer.js placed in FooterComp directory under src. import React, { Component } from 'react';import '../App.css';class Footer extends Component { componentDidMount() { console.log('in componentDidMount of Footer') } render() { console.log('in render of Footer') return ( <div className="App"> <h1>Edited by Me</h1> </div> ); }}export default Footer; Why does this work when I refer my firstcomponent from my index.js but doesnt work for footer component when trying to import in my firstcomponent? Errormessage: Error: Cannot find module '../FooterComp/Footer' Also note that if i place Footer component in the same directory as Firstcomponent and adjust the path it works fine
Now provide the response and nothing else.
| There’s limitation when using dynamic imports with variable parts. Webpack Docs It is not possible to use a fully dynamic import statement, such as import(foo). Because foo could potentially be any path to any file in your system or project. The import() must contain at least some information about where the module is located. Bundling can be limited to a specific directory or set of files so that when you are using a dynamic expression - every module that could potentially be requested on an import() call is included.For example, import( ./locale/${language}.json ) will cause every .json file in the ./locale directory to be bundled into the new chunk. At run time, when the variable language has been computed, any file like english.json or german.json will be available for consumption. In your case, during build time for dynamic import in FirstComponent component, bundling was limited to directory where the FirstComponent component was i.e. Components directory. What it means is that, webpack will find all the files that are in the Components directory and then create chunks for them. Then at runtime when dynamic import is called, webpack will serve the chunk that corresponds to the value passed in. Since you passed path= '../FooterComp/Footer' has no corresponding chunk so webpack will throw the error. This is also same for Dynamic component. If you try to dynamically import with variable parts for the files that are outside src folder, you will get same error. So to solve this you have couple of options place both files in same folder i.e 'src/Components/FirstComponent.js''src/Components/Footer.js' And use // In FirstComponent.js componentDidMount() { const { path } = this.props; import(`${path}`) .then(module => this.setState({ module: module.default })) }{Component && <Component path='./Footer' />} // Index.js be more specific as possible i.e // In FirstComponent.js componentDidMount() { const { path } = this.props; import(`../FooterComp/${path}`) .then(module => this.setState({ module: module.default })) } And use {Component && <Component path='Footer' />} // In index.js | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/54254553', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/10656340/']} | jdg_382549 |
stackexchange | llm_judgeable_groundtruth_similarity | 56303331 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
def post(self): if db.users.find({"email": email}).count() != 0: abort(400, message="email is alread used.") DeprecationWarning: count is deprecated. Use Collection.count_documents instead. I'm making authentication server with Python-Flask and PyMongo package. Every time post() method is called, above deprecation warning message is displayed. def post(self): if db.users.find({"email": email}).count_documents() != 0: abort(400, message="email is alread used.") However, if I change count() to count_documents() , following error message comes out. AttributeError: 'Cursor' object has no attribute 'count_documents' How do I call count_documents() correctly after find() is called?
Now provide the response and nothing else.
| The method count_documents is part of the collection , not the cursor ( find returns a cursor).Please see the PyMongo documentation regarding the method for more information and a note regarding some operators. def post(self): if db.users.count_documents({"email": email}) != 0: abort(400, message="email is alread used.") | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/56303331', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/9225379/']} | jdg_382550 |
stackexchange | llm_judgeable_groundtruth_similarity | 14993309 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
On our ASP.Net website, we've had some requests timeout. AppDynamics shows that the SQL procedure calls are returning in a matter of seconds, but we're spending 100+ seconds in SNIReadSyncOverAsync. Does anyone know what this method is / does and why it would be taking that much time? We're not using EF which is referenced in every question / post I've been able to find about it. Thanks in advance Update It's been a while and while we never came to a resolution as to why all of the time was being spent in SNIReadSyncOverAsync, I have a few thoughts. I think that in this case, it may have been the way that specific version of AppDynamics was reporting the time spent on the SQL calls, but I have no real data to back that up, just my guess from what I observed. We eventually stopped seeing the time reported as being spent in SNIReadSyncOverAsync and it shifted to the queries themselves timing out. That still didn't make a lot of sense because the same queries would run instantly in SSMS on the same database. The ultimate answer ended up being related to ARITHABORT causing our application and SSMS to use two different execution plans (see https://dba.stackexchange.com/a/9841 ), explaining why we couldn't reproduce the timeouts with SSMS. Once we resolved that, we were able to identify a few portions of the procedure that needed tuning and we haven't run into the unexplained timeouts or SNIReadSyncOverAsync since.
Now provide the response and nothing else.
| Not sure if you already have resolved this, but: SNI is SQL Server Network Interface, and the mentioned method exists in most ADO.NET full call stacks that wait for data from SQL Server. This is regardless of whether the higher-level implementation is EF, raw ADO.NET or whatever. I'm not sure which metric or signal AppDynamics uses to capture the completion of a stored procedure execution, but you could be seeing this kind of behavior if your stored procedure completes relatively fast, but transmitting the query result from the server to your client takes a while. Without knowing more about your infrastructure, it is very hard to help further. If the problem still persists, I would recommend running the same query in SQL Server Management studio with SET STATISTICS TIME ON and "Include Client Statistics" switched to on. Perhaps those numbers would give you an idea on whether data transfer is actually the problem. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/14993309', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/65560/']} | jdg_382551 |
stackexchange | llm_judgeable_groundtruth_similarity | 8067643 |
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 trying to search a descending sorted array using this binary search code. However, after I sort it, and try to search, it doesn't come back with any result, just a loading icon that never goes away as if it has an infinite loop. I'm not sure what the problem is because the code looks logical. This is aspx with 4.0 framework, c#. Thanks in advance! protected void Button2_Click(object sender, EventArgs e) { String item = TextBox1.Text; int target = Convert.ToInt16(item); int mid, first = 0, last = mynumbers.Length - 1; //for a sorted array with descending values while (first<=last) { mid = (first + last) / 2; if (target < mynumbers[mid]) first = mid + 1; if (target > mynumbers[mid]) last = mid - 1; else Label11.Text = "Target " + item + " was found at index " + mynumbers[mid]; }
Now provide the response and nothing else.
| There is a binary search in the Array class: int index = Array.BinarySearch(mynumbers, target); For descending order, this can be easily accomplished with a ReverseComparer which is easy to write like: public class ReverseComparer<T> : IComparer<T> { public int Compare(T x, T y) { return Comparer<T>.Default.Compare(y, x); } } Then: int index = Array.BinarySearch(numbers, 7, new ReverseComparer<int>()); If this is an academic exercise and you must use a custom search, of course, this won't apply. If it's got to be a custom algorithm for a class, then the problems are that you must break out of the loop when found, and the index is at mid , not at mynumbers[mid] : //for a sorted array with descending values while (first<=last) { mid = (first + last) / 2; if (target < mynumbers[mid]) { first = mid + 1; } if (target > mynumbers[mid]) { last = mid - 1; } else { // the index is mid, not mynumbers[mid], and you need to break here // once found or it's an infinite loop once it finds it. Label11.Text = "Target " + item + " was found at index " + mid; break; } } And actually, I'd probably set a bool flag instead to keep the algorithm pure and not mix the find with the output concerns, this will also make it easier to tell what happened if you exit the loop with not found: bool found = false; //for a sorted array with descending values while (!found && first<=last) { mid = (first + last) / 2; if (target < mynumbers[mid]) { first = mid + 1; } if (target > mynumbers[mid]) { last = mid - 1; } else { // You need to stop here once found or it's an infinite loop once it finds it. found = true; } } Label11.Text = found ? "Item " + item + " was found at position " + mid : "Item " + item + " was not found"; | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/8067643', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1038020/']} | jdg_382552 |
stackexchange | llm_judgeable_groundtruth_similarity | 11361431 |
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: client := &http.Client{}/* Authenticate */req, err := http.NewRequest("GET", "http://164.99.113.32/Authenticate", nil)req.SetBasicAuth("<username>","<password>")resp, err := client.Do(req)if err != nil { fmt.Printf("Error : %s", err)}/* Get Details */req.URL, _ = url.Parse("http://164.99.113.32/Details")resp, err = client.Do(req)if err != nil { fmt.Printf("Error : %s", err)} Now, the second http call is failing with a 401 access-denied error. A different REST client (a firefox plugin) correctly gets the details from the server, so I know that nothing is wrong on the server side. Do I need to pass some kind of session string or something that we got in the previous request ?
Now provide the response and nothing else.
| Okay. I have resolved this. I just needed to create a cookie jar. I am surprised that this is not handled by default by the golang httpreq/client class. The code that I had to use was: type myjar struct { jar map[string] []*http.Cookie}func (p* myjar) SetCookies(u *url.URL, cookies []*http.Cookie) { fmt.Printf("The URL is : %s\n", u.String()) fmt.Printf("The cookie being set is : %s\n", cookies) p.jar [u.Host] = cookies}func (p *myjar) Cookies(u *url.URL) []*http.Cookie { fmt.Printf("The URL is : %s\n", u.String()) fmt.Printf("Cookie being returned is : %s\n", p.jar[u.Host]) return p.jar[u.Host]} and then in main: jar := &myjar{} jar.jar = make(map[string] []*http.Cookie) client.Jar = jar Works. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/11361431', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/153586/']} | jdg_382553 |
stackexchange | llm_judgeable_groundtruth_similarity | 6825722 |
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 been educating myself. Reading this : The engine evaluates each rule from right to left, starting from the rightmost selector (called the "key") and moving through each selector until it finds a match or discards the rule. (The "selector" is the document element to which the rule should apply.) For example: ul li a {...}#footer h3 {...}* html #atticPromo ul li a {...] Now, some example code SASS outputs for me: #content #blog { /* ... */}/* line 85, ../sass/screen.scss */#content #flickr { /* ... */}#content #flickr div p { /* ... */} This seems a bit awkward.. am I doing something wrong? Is this a communication problem between me and Sass? Are we losing it? Edit :Some SCSS code: #flickr { @include columns(5,8); background: url('../img/ipadbg.png') no-repeat; #ipod-gloss { z-index: 999; position: relative; } div { margin-top: -80px; margin-right: 20px; h2 { color: $white; font-size: 24px; } p { margin-top: 40px; } }} Side Bonus! : The article says browsers (or at least Firefox) search the selectors from right to left. I couldn't understand why this is a more efficient why. Any clues?
Now provide the response and nothing else.
| You have to find your compromise between maintainability (nesting makes it easier to find your way around in the stylesheet) and rendering performance. A rule of thumb says you should try to restrict yourself to a three-level nesting and you should avoid to nest IDs if it's not necessary. However, I think nesting too much is not the biggest issue. As soon as I became aware of the power of mixins, I used them a lot. For example, this is my often used button mixin: @mixin small-button($active-color: $active-color, $hover-color: $button-hover-color, $shadow: true) display: inline-block padding: 4px 10px margin: right: 10px bottom: 10px border: none background-color: $button-color color: $font-color-inv +sans-serif-font(9px, 700) text-align: center text-transform: uppercase cursor: pointer @if $shadow +light-shadow &:hover text-decoration: none background-color: $hover-color &:last-child margin-right: 0 a color: $font-color-inv &, &:hover text-decoration: none &.disabled +opacity(0.75) &:hover background-color: $button-color &.active background-color: $active-color &.disabled:hover background-color: $active-color You see, quite a bit code. Applying such mixins to many elements on your page will result in a big CSS file which takes longer to be interpreted. In the old fashioned CSS-way you would give each button element e.g. the class .small-button. But this method pollutes your markup with unsemantic classes. Sass provides a solution though: selector inheritance via the @extend directive . If you set defaults for your parameter of the mixin, you can also provide a simple class, which uses the mixins with your default: // Use this mixin via @extend if you are fine with the parameter defaults.small-button +small-button And then you can just inherit from this class in various contexts: #admin-interface input[type=submit] @extend .small-button The resulting CSS statement aggregates all usages of .small button into one rule with comma-separated selectors: .small-button, #admin-interface input[type=submit] { display: inline-block; ...} Concluding, a naive usage of Sass can effect your CSS performance. Used wisely, however, it is maintainable thanks to well-structured and DRY code, it leads to proper separation of markup and styling (semantic classes only) and allows for smart and performant CSS code. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/6825722', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/119959/']} | jdg_382554 |
stackexchange | llm_judgeable_groundtruth_similarity | 29275576 |
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 file, generated by shell command - stat: path=/etc/swift/account.ring.gz get_md5=yes register: account_builder_stat- name: write account.ring.gz file shell: swift-ring-builder account.builder write_ring <--- rewrite account.ring.gz chdir=/etc/swift changed_when: ??? account_builder_stat.changed ??? <-- no give desired effect How can I check that the file has been changed?
Now provide the response and nothing else.
| - stat: path=/etc/swift/account.ring.gz get_md5=yes register: before- name: write account.ring.gz file shell: swift-ring-builder account.builder write_ring # update account.ring.gz chdir=/etc/swift changed_when: False # without this, as long as swift-ring-builder exits with # return code 0 this task would always be reported as changed- stat: path=/etc/swift/account.ring.gz get_md5=yes register: after- debug: msg='report this task as "changed" if file changed' changed_when: "'{{before.stat.md5}}' != '{{after.stat.md5}}'"- debug: msg='execute this task if file changed' when: "'{{before.stat.md5}}' != '{{after.stat.md5}}'" If what you really want is to report the task 'write account.ring.gz file' as changed or not changed based on outcome of swift-ring-builder then you have to run a mini shell script. Something like this (not tested): - name: write account.ring.gz file shell: bfr=`md5sum account.ring.gz`; swift-ring-builder account.builder write_ring; aftr=`md5sum account.ring.gz`; test $bfr -eq $aftr chdir=/etc/swift or if I remember the md5sum options correctly: - name: write account.ring.gz file shell: echo `md5sum account.ring.gz` account.ring.gz > /tmp/ff; swift-ring-builder account.builder write_ring; md5sum -c /tmp/ff chdir=/etc/swift | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/29275576', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1491378/']} | jdg_382555 |
stackexchange | llm_judgeable_groundtruth_similarity | 2821030 |
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:
First I note that $limsup_{x\in[0,1)}=n^2$, although I do not know how to prove this rigorously. This leads me to believe that the function $f_n(x)=n^2x(1-x^2)^n$ does not uniformly convergence on $[0,1)$, because this implies that given a fixed n, $\forall \epsilon>0 , \exists x\in[0,1)$ s.t $|f_n(x)-n^2|<\epsilon$, and so this series can't uniformly converge to a certain value because $n^2$ is different (monotonely increasing) for each n. If it's not obvious, I need a bit of help clarifying things.
Now provide the response and nothing else.
| The typical proof that your $A \times B$ satisfies the universal property of the coproduct in $\mathbf{Ab}$ is as follows:if $f: A \to C$ and $g: B \to C$ are two homomorphisms of abelian groups, then there is the induced homomorphism $h: A \times B \to C$ defined by $h(a,b) = f(a) + g(b)$. In order for this to be a homomorphism, $C$ must be abelian, for$$ h(a,b) + h(a',b') = f(a) + g(b) + f(a') + g(b') $$and$$ h(a+a',b+b') = f(a) + f(a') + g(b) + g(b'),$$so $f(a')$ and $g(b)$ must commute for all $a' \in A$, $b \in B$ in order for the desired homomorphism to actually be a homomorphism. | {} | {'log_upvote_score': 5, 'links': ['https://math.stackexchange.com/questions/2821030', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/489046/']} | jdg_382556 |
stackexchange | llm_judgeable_groundtruth_similarity | 35236834 |
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 was playing around with labels as values and ended up with this code. int foo = 0;goto *foo; My C/C++ experience tells me *foo means dereference foo and that this won't compile because foo isn't a pointer. But it does compile. What does this actually do? gcc (Ubuntu 4.9.2-0ubuntu1~12.04) 4.9.2 , if important.
Now provide the response and nothing else.
| This is a known bug in gcc. gcc has a documented extension that permits a statement of the form goto *ptr; where ptr can be any expression of type void* . As part of this extension, applying a unary && to a label name yields the address of the label, of type void* . In your example: int foo = 0;goto *foo; foo clearly is of type int , not of type void* . An int value can be converted to void* , but only with an explicit cast (except in the special case of a null pointer constant, which does not apply here). The expression *foo by itself is correctly diagnosed as an error. And this: goto *42; compiles without error (the generated machine code appears to be a jump to address 42 , if I'm reading the assembly code correctly). A quick experiment indicates that gcc generates the same assembly code for goto *42; as it does for goto *(void*)42; The latter is a correct use of the documented extension, and it's what you should probably if, for some reason, you want to jump to address 42. I've submitted a bug report -- which was quickly closed as a duplicate of this bug report , submitted in 2007. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/35236834', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/4434762/']} | jdg_382557 |
stackexchange | llm_judgeable_groundtruth_similarity | 54101 |
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 want to prove the determinantal ideals over a field are prime ideals. To be concrete: For simplicity, let $I=(x_{11}x_{22}-x_{12}x_{21},x_{11}x_{23}-x_{13}x_{21},x_{12}x_{23}-x_{13}x_{22})$ be an ideal of the polynomial ring $k[x_{11},\ldots,x_{23}]$. I have no idea how to prove that $I$ is a radical ideal (i.e. $I=\sqrt{I}$). Could anyone give some hints? Generally, let $K$ be an algebraically closed field, then $\{A\mid\mathrm{Rank}(A)\leq r\}\subseteq K^{m\times n}$ is an irreducible algebraic set (I first saw this result from this question ). And I tried to prove this by myself, then I have proved it (when I see the "Segre embedding"). But I have no idea how to show that the "determinantal ideals" are radical ideals (I hope this is true). BTW, is the statement that the determinantal ideals over a field are prime ideals true ? Thanks.
Now provide the response and nothing else.
| There are several ways to prove that $I$ is radical. By the way, the statement that $I$ is prime is equivalent to $I$ being radical and the zero set of $I$ being an irreducible algebraic set. An approach using Gröbner bases can be found in Chapter 16 of Miller-Sturmfels, Combinatorial Commutative Algebra An approach using sheaf cohomology can be found in Sections 6.1-6.2 of Weyman, Cohomology of Vector Bundles and Syzygies . This requires a lot more background knowledge. There is also the approach using induction on the size of the matrix and localization arguments in Chapter 2 of Bruns-Vetter, Determinantal Rings. Link to book: http://www.home.uni-osnabrueck.de/wbruns/brunsw/detrings.pdf | {} | {'log_upvote_score': 5, 'links': ['https://math.stackexchange.com/questions/54101', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/4396/']} | jdg_382558 |
stackexchange | llm_judgeable_groundtruth_similarity | 153121 |
Below is a question asked on the forum cs.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Data only accessible in a scope, seems to still be maintained by the stack. What is the reason that entering and exiting scopes (in general) does not do the same "prologue and epilogue" instructions that are done when entering and exiting functions? What test1 and test2 show, in test2 8 byte is allocated in the stack, but it has already left the scope for int a when declaring int b . The ISA is x86 (compiled on godbolt.org with x86-64) but I assume this behavior might exist in many different standards, and ask from a more general computer science point of view. void test1(){ int a; { a = 141; } a = 257;}test1(): push rbp mov rbp, rsp mov DWORD PTR [rbp-4], 141 mov DWORD PTR [rbp-4], 257 nop pop rbp retvoid test2(){ { int a = 141; } int b = 257;}test2(): push rbp mov rbp, rsp mov DWORD PTR [rbp-4], 141 mov DWORD PTR [rbp-8], 257 nop pop rbp ret
Now provide the response and nothing else.
| Sure. Pick a block cipher (i.e., pseudorandom permutation ), $E_K$ , and a random key for it, $K$ . Let $x_i=E_K(i)$ . Then this has the properties you are looking for. Short explanation: As the block cipher $E_K$ maps each n -bit value uniquely to another n -bit value, all the resulting values must be different for different input values.Effectively that means $E_K$ creates a permutation of n -bit values that can be varied by changing $K$ . | {} | {'log_upvote_score': 6, 'links': ['https://cs.stackexchange.com/questions/153121', 'https://cs.stackexchange.com', 'https://cs.stackexchange.com/users/152243/']} | jdg_382559 |
stackexchange | llm_judgeable_groundtruth_similarity | 174459 |
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:
Every EMC filter I've seen has capacitors between the AC lines and earth, configured like this: simulate this circuit – Schematic created using CircuitLab Why are the caps not configured like this? simulate this circuit What is the advantage of having the extra cap from neutral to ground? It seems like it would reduce the capacitance to ground, and thus the effectiveness of the filter. Is it a safety issue, in case the capacitors fail short? But isn't avoiding that the point of using Y-rated capacitors?
Now provide the response and nothing else.
| So you have 3-phase power. There is noise that is line-to-line and noise that is common mode. The caps across the lines are in the right position to filter the line-to-line noise, and the single cap to ground can filter the common mode noise. If you used your method, the capacitance between phases would be less. There may also be a consideration that the X capacitors are cheaper and smaller for the same capacitance (if you can even buy that capacitance) as compared to the Y capacitor (because the requirements for Y caps are so much more stringent), so it makes sense to minimize the number of Y capacitors (it also reduces the likelihood of an unsafe failure by 3:1). | {} | {'log_upvote_score': 4, 'links': ['https://electronics.stackexchange.com/questions/174459', 'https://electronics.stackexchange.com', 'https://electronics.stackexchange.com/users/7523/']} | jdg_382560 |
stackexchange | llm_judgeable_groundtruth_similarity | 26942150 |
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 having difficulty in importing a local go file into another go file. My project structure is like something below -samplego--pkg--src---github.com----xxxx-----a.go-----b.go--bin I am trying to import a.go inside b.go. I tried the following, import "a"import "github.com/xxxx/a" None of these worked..I understand I have to meddle up with GOPATH but I couldn't get it right. Presently my GOPATH is pointing to samplego(/workspace/samplego).I get the below error cannot find package "a" in any of:/usr/local/go/src/pkg/a (from $GOROOT)/workspace/samplego/src/a (from $GOPATH) Also, how does GOPATH work when these source files are imported into another project/module? Would the local imports be an issue then? What is the best practice in this case - is it to have just one go file in module(with associated tests)?
Now provide the response and nothing else.
| Any number of files in a directory are a single package; symbols declared in one file are available to the others without any import s or qualifiers. All of the files do need the same package foo declaration at the top (or you'll get an error from go build ). You do need GOPATH set to the directory where your pkg , src , and bin directories reside. This is just a matter of preference, but it's common to have a single workspace for all your apps (sometimes $HOME ), not one per app. Normally a Github path would be github.com/username/reponame (not just github.com/xxxx ). So if you want to have main and another package, you may end up doing something under workspace/src like github.com/ username/ reponame/ main.go // package main, importing "github.com/username/reponame/b" b/ b.go // package b Note you always import with the full github.com/... path: relative imports aren't allowed in a workspace. If you get tired of typing paths, use goimports . If you were getting by with go run , it's time to switch to go build : run deals poorly with multiple-file main s and I didn't bother to test but heard (from Dave Cheney here ) go run doesn't rebuild dirty dependencies. Sounds like you've at least tried to set GOPATH to the right thing, so if you're still stuck, maybe include exactly how you set the environment variable (the command, etc.) and what command you ran and what error happened. Here are instructions on how to set it (and make the setting persistent) under Linux/UNIX and here is the Go team's advice on workspace setup . Maybe neither helps, but take a look and at least point to which part confuses you if you're confused. | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/26942150', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1965994/']} | jdg_382561 |
stackexchange | llm_judgeable_groundtruth_similarity | 191207 |
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 wrote an answer here , which I'm not sure works. The sum rule for differentiation of two functions says that $D(u+v) = D(u) + D(v)$ where $D$ indicates the derivative, and $u$ and $v$ two functions. The sum rule can get extended to any finite set of functions. Since numbers can get regarded as functions, this implies that for any finite series $S=a + b + \dots+z$ we can evaluate $D(S).$ Can we extend the sum rule to differentiation of convergent infinite series? Divergent infinite series? Why or why not?
Now provide the response and nothing else.
| Not really. Actually, what you want is uniform convergence and majorant series. DEFINITION 1 Let $f_n(x)$ be a sequence of functions. In particular, suppose $f_n(x)=\sum_{k=0}^n g_k(x)$ for some sequence $\{g_k\}_{k\in \mathbb N}$ of functions. Let $D$ be the set of points $x$ such that $\lim f_n(x)$ exists. Call $D$ the domain of convergence of $f=\lim f_n$ . An important property is a series might have is being majorant. DEFINITION 2 We say that a series of functions is majorant in a certain domain $D'$ if there exists a convergent positive series $A=\sum a_k$ such that, for each $x$ in that domain $D'$ we have $|g_k(x)|\leq a_k$ . Given a series $f=\lim f_n=\lim\sum^n g_k$ , we say that $f$ converges absolutely if $f^*=\lim\sum^n |g_k|$ converges. (Thus, a majorant series is absolutely convergent.) Yet another important case scenario is uniform convergence: DEFINITION 3 (Uniform convergence) We say a series of functions converges uniformly in $D$ if for all $\epsilon>0$ there is an $N$ (depending only on $\epsilon$ ), such that $n\geq N$ implies $$|f(x)-f_n(x)|<\epsilon $$ We usually say $N$ is independent of the choice of $x$ , too. You can picture this behaviour as follows: Each partial sum is always contained in the strip inside $f(x)+\epsilon$ and $f(x)-\epsilon$ of width $2\epsilon$ . In particular, every majorant series converges uniformly. This is known as Weierstrass' $M$ criterion. For majorant series, the following is valid: THEOREM 1 If the series $\sum u_k(x)$ composed of functions with continuous derivates on $[a,b]$ converges to a sum function $s(x)$ and the series $$\sum u'_k(x)$$ composed of this derivatives is majorant on $[a,b]$ , then $$s'(x)=\sum u'_k(x)$$ This stems from THEOREM 2 Let $s(x)=\sum u_k(x)$ be a series of continuous functions, majorant on some $D$ . Then, if $x$ and $\alpha$ are in $D$ $$\int_\alpha^x s(t)dt=\sum\int_\alpha^xu_k(t)dt$$ You can read this in much more detail, and find proofs, in (IIRC) Apostol's Calculus (Vol.1) | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/191207', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/11300/']} | jdg_382562 |
stackexchange | llm_judgeable_groundtruth_similarity | 300122 |
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:
So I had a RAID 1 with two hard disk. One hard disk failed, then I replaced it and I reinstalled on this new hard disk a fresh Linux. Now If I type fdisk -l I get: root@ns354729:/mnt/sdb2# fdisk -lDisk /dev/sda: 2000.4 GB, 2000398934016 bytes255 heads, 63 sectors/track, 243201 cylinders, total 3907029168 sectorsUnits = sectors of 1 * 512 = 512 bytesSector size (logical/physical): 512 bytes / 512 bytesI/O size (minimum/optimal): 512 bytes / 512 bytesDisk identifier: 0xbb5259be Device Boot Start End Blocks Id System/dev/sda1 * 4096 1495042047 747518976 83 Linux/dev/sda2 1495042048 1496088575 523264 82 Linux swap / SolarisDisk /dev/sdb: 750.2 GB, 750156374016 bytes255 heads, 63 sectors/track, 91201 cylinders, total 1465149168 sectorsUnits = sectors of 1 * 512 = 512 bytesSector size (logical/physical): 512 bytes / 512 bytesI/O size (minimum/optimal): 512 bytes / 512 bytesDisk identifier: 0x00025c91 Device Boot Start End Blocks Id System/dev/sdb1 4096 20975616 10485760+ fd Linux raid autodetect/dev/sdb2 20975617 1464092672 721558528 fd Linux raid autodetect/dev/sdb3 1464092673 1465144064 525696 82 Linux swap / Solaris I would like to acces the second hard disk (sdb) so I try to mount sdb2 like this: mount /dev/sdb2 /mnt THis says: root@ns354729:/mnt/sdb2# mount /dev/sdb2 /mntmount: block device /dev/sdb2 is write-protected, mounting read-onlymount: you must specify the filesystem type So I tried to give: mount -t ext4 /dev/sdb2 /mnt and I got: mount: wrong fs type, bad option, bad superblock on /dev/sdb2, missing codepage or helper program, or other error In some cases useful info is found in syslog - try dmesg | tail or so And this says: root@ns354729:/mnt/sdb2# dmesg | tailufs_read_super: bad magic numberVFS: Can't find a romfs filesystem on dev sdb2.UDF-fs: warning (device sdb2): udf_load_vrs: No VRS foundUDF-fs: warning (device sdb2): udf_fill_super: No partition found (2)XFS (sdb2): Invalid superblock magic number(mount,18813,1):ocfs2_fill_super:1038 ERROR: superblock probe failed!(mount,18813,1):ocfs2_fill_super:1229 ERROR: status = -22GFS2: not a GFS2 filesystemGFS2: gfs2 mount does not existEXT4-fs (sdb2): VFS: Can't find ext4 filesystem any help?
Now provide the response and nothing else.
| You need to assemble the (degraded) RAID array, using something like: mdadm --assemble --readonly /dev/md0 /dev/sdb2 Of course, pick a number besides md0 if that's already in use. Then you can mount /dev/md0 (or, if it is actually LVM, etc., continue down the chain). You can, in the case of RAID1, also do this using loopback devices & an offset, but that's much more of a pain, and really is only worth attempting if the mdadm metadata has been destroyed. | {} | {'log_upvote_score': 4, 'links': ['https://unix.stackexchange.com/questions/300122', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/182915/']} | jdg_382563 |
stackexchange | llm_judgeable_groundtruth_similarity | 417041 |
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 struggle to understand the effects of the following command: yes | tee hello | head On my laptop, the number of lines in 'hello' is of the order of 36000, much higher than the 10 lines displayed on standard output. My questions are: When does yes , and, more generally, a command in a pipe, stop? Why is there a mismatch between the two numbers above. Is it because tee does not pass the lines one by one to the next command in the pipe?
Now provide the response and nothing else.
| :> yes | strace tee output | head[...]read(0, "y\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\n"..., 8192) = 8192write(1, "y\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\n"..., 8192) = 8192write(3, "y\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\n"..., 8192) = 8192read(0, "y\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\n"..., 8192) = 8192write(1, "y\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\ny\n"..., 8192) = -1 EPIPE (Broken pipe)--- SIGPIPE {si_signo=SIGPIPE, si_code=SI_USER, si_pid=5202, si_uid=1000} ---+++ killed by SIGPIPE +++ From man 2 write : EPIPE fd is connected to a pipe or socket whose reading end is closed. When this happens the writing process will also receive a SIGPIPE signal. So the processes die right to left. head exits on its own, tee gets killed when it tries to write to the pipeline the first time after head has exited. The same happens with yes after tee has died. tee can write to the pipeline until the buffers are full. But it can write as much as it likes to a file. It seems that my version of tee writes the same block to stdout and the file. head has 8K in its (i.e. the kernel's) read buffer. It reads all of it but prints only the first 10 lines because that's its job. | {} | {'log_upvote_score': 4, 'links': ['https://unix.stackexchange.com/questions/417041', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/212582/']} | jdg_382564 |
stackexchange | llm_judgeable_groundtruth_similarity | 1048642 |
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:
Evaluate $$ \int_{0}^{\frac{\pi}{2}} \frac{\sin^2 nx}{\sin^2 x} \text{d}x$$ where $n\in\mathbb{N}$ This one is another intriguing question from my worksheet. I'm only allowed to use elementary methods and high school math. However, I can't see a way to do this without derivative under the integral (which is not allowed). Please Help! Thanks.
Now provide the response and nothing else.
| Let, $$\text{I(n)}=\displaystyle \int_{0}^{\frac{\pi}{2}} \frac{\sin^2 nx}{\sin^2 x} \text{d}x$$ and $\text{J}= \text{I(n) - I(n-1)}=\displaystyle \int_{0}^{\frac{\pi}{2}} \frac{\sin^2nx-\sin^2(n-1)x}{\sin^2 x} \text{d}x$ $=\displaystyle \int_{0}^{\frac{\pi}{2}} \frac{\sin(2n-1)x\times\sin x}{\sin^2 x} \text{d}x$ [Using $(\sin^2a - \sin^2b) = \sin(a+b)\times \sin(a-b)$ ] $=\displaystyle \int_{0}^{\frac{\pi}{2}} \frac{\sin(2n-1)x}{\sin x} \text{d}x$ Now, consider $$ \text{S}=\cos (2x) + \cos(4x) + \cos(6x) +......+ \cos(2n-2)x = \frac {\sin(n-1)x \times \cos nx}{\sin x}$$ $=\dfrac {2\sin(n-1)x \times \cos nx}{2\sin x}$ $=\dfrac {\sin(2n-1)x - \sin x}{2\sin x}$ $\implies \text{J}=\displaystyle \int_{0}^{\frac{\pi}{2}}(2\text{S}+1) \: \text{d}x$ $=\dfrac{\pi}{2}$ $\implies \text{I(1), I(2), I(3) ..... I(n)}$ form an Arithmetic Progression Since $\text{I(1)}=\dfrac{\pi}{2}$ , $\text{I(n)}=\boxed{\dfrac{n\pi}{2}}$ | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/1048642', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/130750/']} | jdg_382565 |
stackexchange | llm_judgeable_groundtruth_similarity | 1081633 |
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 to find the complex roots of $x^2-2ax+a^2+b^2$? I tried using the quadratic formula: $$ x_{1,2} = \frac{2a \pm \sqrt {4a^2-4b^2}}{2} = {a \pm \sqrt {a^2-b^2}} = a\pm \sqrt{a-b}\sqrt{a+b}$$ I tried to represent each root as $x+iy$ but got stuck along the way.What should I do? Thanks
Now provide the response and nothing else.
| Your equation can be rewritten as$$(x-a)^2=-b^2\iff x-a=\pm ib$$so the roots are $x_{1,2}=a\pm ib$. The quadratic formula also gives the right answer, but it should be$$x_{1,2}=\frac{2a\pm\sqrt{4a^2-4(a^2+b^2)}}2=a\pm\sqrt{-b^2}=a\pm ib$$ | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/1081633', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/188391/']} | jdg_382566 |
stackexchange | llm_judgeable_groundtruth_similarity | 1980452 |
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 packaging a Java library as a JAR, and it's throwing many java.lang.IncompatibleClassChangeError s when I try to invoke methods from it. These errors seem to appear at random. What kinds of problems could be causing this error?
Now provide the response and nothing else.
| This means that you have made some incompatible binary changes to the library without recompiling the client code. Java Language Specification §13 details all such changes, most prominently, changing non- static non-private fields/methods to be static or vice versa. Recompile the client code against the new library, and you should be good to go. UPDATE: If you publish a public library, you should avoid making incompatible binary changes as much as possible to preserve what's known as "binary backward compatibility". Updating dependency jars alone ideally shouldn't break the application or the build. If you do have to break binary backward compatibility, it's recommended to increase the major version number (e.g. from 1.x.y to 2.0.0) before releasing the change. | {} | {'log_upvote_score': 9, 'links': ['https://Stackoverflow.com/questions/1980452', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/17675/']} | jdg_382567 |
stackexchange | llm_judgeable_groundtruth_similarity | 299286 |
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:
The following is a quote from an answer I was given to this previous question of mine : The definition of the expectation value of an operator $A$ is $$\begin{equation}\langle A\,\rangle=\int{\psi^* (x) A(x) \psi (x) dx}\end{equation}\tag{1}$$ (because it represents "the value of the variable" $A(x)$ times "the probability of being in that configuration" $P(x)=\psi^* (x) \psi (x)$) and for the particular case of the expectation value of the position operator $$\begin{equation}\langle x\rangle=\int{x \psi^* (x) \psi (x) dx}\end{equation}\tag{2}$$ Ever since I asked that question I have been using equation $(1)$without fully understanding why for a arbitrary operator $A$ its expectation value takes the form \begin{equation}\int{\psi^* (x) A(x) \psi (x) dx}\end{equation} I understand that the probability is given by $$\begin{equation}\int{\psi^* (x) \psi (x) dx}=\int |\psi(x)|^2dx\end{equation}$$ So equation $(2)$ makes sense to me as it is simply $$\langle x \rangle=\int x|\psi(x)|^2dx$$which is "the value of the variable times the probability of being in that configuration" as mentioned in the quote. But for equation $(1)$ the arbitrary operator $A$ is $\color{red}{\text{in-between}}$ the $\psi^*(x)$ and $\psi(x)$. So unless I can rewrite $(1)$ in the form of "value times probability": $$\begin{equation}\langle A\,\rangle=\int{A(x)\psi^* (x) \psi (x) dx}=\int A|\psi(x)|^2dx\end{equation}\tag{3}$$ I fail to see how equation $(1)$ gives the expectation value. But I already know that equation $(3)$ is wrong since in equation $(1)$ the operator $A$ is acting on $\psi(x)$, so it doesn't make any sense to move the operator to the front of the integrand just to make it look like equation $(2)$. Can anyone please explain to me why equation $(1)$ is justified as the expectation value even though the operator is in the middle?
Now provide the response and nothing else.
| There is a slight, but important aspect you are missing here. The expectation value of the observable $A$ is defined as $$\langle A\rangle_\psi=\int\psi^*(x)A\psi(x)dx$$ where as the probability of being in the configuration $\psi(x)$ is $$P=\int\psi^*(x)\psi(x)dx$$ But I already know that equation $(3)$ is wrong since in equation $(1)$ the operator $A$ is acting on $\psi(x)$, so it doesn't make any sense to move the operator to the front of the integrand just to make it look like equation $(2)$. Yes of course. You are right. Now, we see the part you are missing. In quantum mechanics, we define the operators representing observables as Hermitian and an operator has got certain eigen functions. If $\psi(x)$ is such an eigen function of the operator $A$, then you will have the eigen value equation $$A\psi(x)=a\psi(x)$$ where $a$ is the corresponding eigen value which is a real number. In such a case, $$\langle A\rangle_\psi=\int\psi^*(x)a\psi(x)dx=a\int\psi^*(x)\psi(x)dx=aP$$ where $P$ as defined above is the probability that the system can be found in the state $\psi(x)$. Hence we can say that the expectation value of an operator w.r.t a particular state is the eigen value of that state times the probability of being in that state. That's the difference between an expectation value and the eigen value. Unless the wavefunction is normalized ($P=1$), we will not get the eigen value of the operator as it's expectation value. Now, the wavefunction $\psi(x)$ need not be always an eigen function of $A$. In such cases, we expand our wavefunction as a superposition of the eigen functions of the operator $A$ in Dirac's bra-ket notation: $$\vert \psi\rangle=\int d\zeta '\vert\zeta'\rangle\langle\zeta'\vert\psi\rangle $$ where {$\zeta_j$} forms a complete set of eigen functions of $A$ and $\displaystyle{\int d\zeta '\vert\zeta'\rangle\langle\zeta\vert}$ is the identity operator $1$ and $\vert\zeta'\rangle\langle\zeta'\vert$ is the projection operator $\Lambda_{\zeta'}$. The operations all happen in the appropriate Hilbert space spanned by the complete inner products of the eigen kets and eigen bras of the operator. Before we proceed further, let's have a short brief on Dirac's formalism: Short brief on Dirac's bra-ket notation : The ket, like the wavefunction represent a particular state of the system, but it's not actually the wavefunction of the system. It is represented as $\vert\psi\rangle$. The wave function of the system can be derived from the ket, and the ket representing a state, called the state ket, is a vector in the vector space spanned by the eigen kets of the operator $A$, just as like we speak the eigen functions of the operator $A$. Now, for the wavefunction, we have a corresponding complex wave function. Similarly, the complex dual of a state ket is called a state bra and is represented by $\langle\psi\vert$. So, expectation value of some operator of the quantum mechanical system is what we want to measure. The first thing we consider is that we represent the general state ket (which is of course undefined) as a linear superposition of the eigen kets of the operator (which are known, once you solve the eigen value equation). It's like writing a vector as a linear combination of the independent coordinates. However, a vector space is a different thing. But the concept is the same. So, a general state ket $\vert\alpha\rangle$ can be expanded in terms of the complete eigen vectors of the operator $A$ as: $$\vert\alpha\rangle=\sum_{a'}c_{a'}\vert a'\rangle=c_{a'}\vert a'\rangle+c_{a''}\vert a''\rangle+c_{a'''}\vert a'''\rangle+...$$ where the kets $\vert a'\rangle, \vert a''\rangle,\vert a'''\rangle...$ are the eigen kets of $A$ and are complete. The set {$a'$} are the corresponding eigen values. The expansion coefficients $c_{a'},c_{a''},...$ are the probability amplitudes of the corresponding eigen kets. This can be understood in the coming paragraphs where we define the inner product of a ket and a bra. We represent the state of the system in question as a linear combination of the eigen kets of the observable, whose expectation value is to be measured. This vector is represented as a ket and is defined in a complex vector space called the ket space. So, the ket space is spanned by the eigen kets of the operator. This means the eigen kets of the operator forms the basis vectors of our vector space. Since there is a one-to-one correspondence between a ket and the corresponding bra, we can define a space spanned by eigen bras and is called a bra space. If we take the inner product of the state ket and the state bra, defined respectively in the ket space and the bra space, we will get a complete inner product space called the Hilbert space. All the quantum "mechanics" happen in the Hilbert space. Why do we need an inner product space? Well, the ket and bra are complex vectors and they are useless, unless we can extract some information from them. To obtain that, we take the inner product of the ket and bra. The inner product is taken between a bra and a ket. The inner product between the state ket $\vert\alpha\rangle$ and the state bra $\langle\beta\vert$ is denoted as $\langle\beta\vert\alpha\rangle$. It gives the probability amplitude that the system, found initially in the state $\vert\alpha\rangle$ to be found in the state $\vert\beta\rangle$, whose square of the modulus gives the probability of the same. The inner product is a real number. This probability is the fundamental thing that accompanies all the rest of the operations, which you will see in the coming discussions. The probability is a real number and must be positive. So the inner product explained above should be positive. Now lets look back where we defined $c_{a'}$ as the probability amplitude of the state defined by the ket $\vert\alpha\rangle$ to be found in the state $\vert a'\rangle$, which is an eigen state of the operator $A$. For that, we take the inner product of $\vert\alpha\rangle$ with the eigen bra $\langle a'\vert$, we get $$\langle a'\vert\alpha\rangle=\sum_{a'}c_{a'}\langle a'\vert a'\rangle=c_{a'}$$ where we have used an important relation called the orthonormality condition of two kets. If two kets $\vert a'\rangle$ and $\vert a''\rangle$ are orthogonal (independent) and normalized (so that the inner product of the ket with it's own bra gives $1$), then the orthonormality condition states that $$\langle a'\vert a''\rangle=\delta_{a',a''}$$ which is $1$ if the two kets are the same and $0$ when they are not. So, we demand the eigen kets of the operators to be orthonormal so that they satisfy the above orthonormality condition. So, we have got $c_{a'}$ as the probability amplitude of the eigen ket $\vert a'\rangle$. Hence the square of its modulus give us the probability that the system is found to be in the eigen state $\vert a'\rangle$: $$\vert c_{a'}\vert^2=\vert\langle a'\vert\alpha\rangle\vert^2$$ Now, we see that $$\sum_{a'} \vert c_{a'}\vert^2=\sum_{a'}\vert\langle a'\vert\alpha\rangle\vert^2=1$$ a requirement by the probability conservation theorem. Now, what happens if we take the inner product of a general ket and the corresponding bra? That answer will give us the probability to find the system to be in that state. If the state kets are normalized, then this probability will be one. Now, while taking the inner product of a state ket with a state bra, we are combining the two spaces- the ket and bra spaces- somehow to get a complete inner product space called Hilbert space. All the information about the state is hidden in this Hilbert space. So we ask the state ket to reveal some information, for example the energy. We do this by operating the state ket buy the energy operator. Then we will get the value of energy, which is present in the Hilbert space. So, the operations on state ket happens in the Hilbert space. Now, let's see the operation of the operators on the state kets. Its similar to the operation of the operators on a wavefunction. The operator $A$ acting on the general ket $\vert\alpha\rangle$ is given by $$A\vert\alpha\rangle=A\sum_{a'}c_{a'}\vert a'\rangle=A\sum_{a'}\left(\langle a'\vert\alpha\rangle\right)\vert a'\rangle=A\sum_{a'}\vert a'\rangle\langle a'\vert\alpha\rangle$$ When we compare both sides that the effect of $\displaystyle{\sum_{a'}\vert a'\rangle\langle a'\vert}$ is just like operating by the identity operator $1$. Hence $\displaystyle{\sum_{a'}\vert a'\rangle\langle a'\vert}=1$ is regarded as the identity opertor. Now, what does the outer product $\Lambda_{a'}=\vert a'\rangle\langle a'\vert$ gives us? Even though the inner product is a scalar, the outer product is an operator. To see this, let it act on the ket $\vert\alpha\rangle$ $$\Lambda_{a'}\vert\alpha\rangle=\vert a'\rangle\langle a'\vert\vert\alpha\rangle=\vert a'\rangle\left(\langle a'\vert\vert\alpha\rangle\right)=c_{a'}\vert a'\rangle.$$ The ket $\vert\alpha\rangle$ is a combination of the all possible eigen kets. When we operate this ket with $\Lambda_{a'}$, the operator selects the portion of the ket $\vert\alpha\rangle$ parallel to $\vert a'\rangle$. Hence it is known as the projection operator. Comparing the identity operator and the projection operator, we find that $$\sum_{a'} \Lambda_{A'}=1$$ Okay, now we are almost equipped with the tools for the further discussion. We have only considered above discrete spectrum cases only. The above facts holds for continuous spectrum. All we have to do is just replace the summation by an integral and the Kronecker delta symbol by the Dirac delta function. Note: This is not a complete description about Dirac's notation. There are a lot of things to see. However I've limitations here. You can found more illuminating discussions on Dirac's notation in Modern Quantum Mechanics by J. J. Sakurai. Now, we continue. The expectation value is defined as $$\langle A\rangle_\psi=\langle\psi\vert A\vert\psi\rangle$$ Substituting the above expansion of $\vert\psi\rangle$ in the equation, we get $$\begin{align} \langle A\rangle_\psi&=\iint d\zeta'd\zeta''\langle\psi\vert\zeta'\rangle\langle\zeta'\vert A \vert\zeta''\rangle\langle\zeta''\vert\psi\rangle\\ &= \iint d\zeta'd\zeta''\langle\psi\vert\zeta'\rangle\zeta' \delta\left(\zeta''-\zeta'\right)\langle\zeta''\vert\psi\rangle\\&=\int d\zeta' \zeta' \langle\psi\vert\zeta'\rangle\langle\zeta'\vert\psi\rangle\end{align}$$ Now, $\langle\zeta'\vert\psi\rangle$ is defined as an inner product of two kets. It gives the probability that the system is transferred from state $\vert\psi\rangle$ to the state $\vert\zeta'\rangle$ and is the transition probability. If I represent $\langle\zeta'\vert\psi\rangle=c_{\zeta'}$, which in general is a complex number and is the transition amplitude, then $\langle\psi\vert\zeta'\rangle=\langle\zeta'\vert\psi\rangle^*=c^*_{\zeta'}$. Hence $$\langle A\rangle_\psi=\int d\zeta ' \zeta' \vert c_{\zeta'}\vert^2$$ which means the expectation value ofthe operator $A$ is the eigen ket of $A$ times the probability of the system to be found in that particular eigen state of $A$. | {} | {'log_upvote_score': 5, 'links': ['https://physics.stackexchange.com/questions/299286', 'https://physics.stackexchange.com', 'https://physics.stackexchange.com/users/57983/']} | jdg_382568 |
stackexchange | llm_judgeable_groundtruth_similarity | 3276185 |
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 a problem from Introduction to Topology: Pure and Applied by Colin Adams and Robert Franzosa. Problem "Prove that a bijection $f:X→Y$ is a homeomorphism if and only if $f$ and $f^{-1}$ map closed sets to closed sets." Definition "We can paraphrase the definition of homeomorphism by saying that $f$ is a homeomorphism if it is a bijection on points and a bijection on the collections of open sets making up the topologies involved. Every point in $X$ is matched to a unique point in $Y$ , with no points in $Y$ left over. At the same time, every open set in $X$ is matched to a unique open set in $Y$ , with no open sets in $Y$ left over." Thoughts Let $f:X→Y$ be a bijection. Suppose $f^{-1}$ does not map the closed $C'$ to a closed set C. Then $f^{-1}$ does not map the open set $Y-C'$ to an open set $X-C$ . Then $f:X→Y$ is not a homeomorphism. Suppose $f$ maps all closed sets $C$ to all closed sets $C'$ , and $f^{-1}$ maps all closed sets $C'$ to all closed sets $C$ . Then $f$ maps all open sets $X-C$ to open sets $Y-C'$ , and $f^{-1}$ maps all open sets $Y-C'$ to open sets $X-C$ . Then $f:X→Y$ is a homeomorphism.
Now provide the response and nothing else.
| The maps $f$ and $f^{−1}$ are closed iff they are continuous: Suppose $f$ is a homeomorphism and let $A \subset X$ be a closed set. We get that $f(A) = (f^{-1})^{-1}(A) \subset Y$ is closed since $f^{-1}$ is continuous. Analogously $f^{-1}$ is closed. Suppose $f$ and $f^{-1}$ are closed, and let $B \subset Y$ be a closed set. Now we have that $f^{-1}(B) \subset X$ is closed as $f^{-1}$ is a closed map. Therefore $f$ is continuous. Analogously $f^{-1}$ is continuous. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/3276185', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/670874/']} | jdg_382569 |
stackexchange | llm_judgeable_groundtruth_similarity | 3818013 |
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 game to which I recently added a global high score functionality which made a lot of people upset so I want to add the option of disabling it.What I did was this: in my settings activity view, I added the following: <!-- High Score Tracking --> <LinearLayout android:layout_weight="40" android:layout_width="fill_parent" android:layout_height="wrap_content" android:orientation="vertical" android:padding="5dip"> <LinearLayout android:layout_width="fill_parent" android:layout_height="wrap_content"> <CheckBox android:text="@string/EnableHighscoreCBText" android:id="@+id/EnableHighscoreCB" android:layout_width="fill_parent" android:layout_height="wrap_content"> </CheckBox> </LinearLayout> <!-- High score specific settings --> <LinearLayout android:layout_width="fill_parent" android:layout_height="wrap_content" android:orientation="horizontal" android:weightSum="100" android:padding="5dip"> <CheckBox android:text="@string/EnableShareScoresCBText" android:id="@+id/EnableShareScoresCB" android:layout_width="fill_parent" android:layout_height="wrap_content"> </CheckBox> <TextView android:id="@+id/DefaultPlayerNameTv" android:layout_width="wrap_content" android:layout_weight="30" android:layout_height="wrap_content" android:text="@string/pDefName" android:textSize="18sp"> </TextView> <EditText android:id="@+id/PlayerNameEt" android:layout_width="wrap_content" android:layout_height="wrap_content" android:text="@string/pNameDefVal" android:layout_weight="70" android:textSize="18sp" android:maxLength="20"> </EditText> </LinearLayout> </LinearLayout> What I want to do is to disable the entire "High score specific settings" layout when the user unchecks the enable high score tracking check box.I tried disabling it by setting the setEnabled to false, but that didn't work at all.Should I be using a viewgroup or something?Is there a refresh method I should run to apply the change?
Now provide the response and nothing else.
| Add a View.OnClickListener to your CheckBox then pass the View you want to be disabled into the following function... private void enableDisableView(View view, boolean enabled) { view.setEnabled(enabled); if ( view instanceof ViewGroup ) { ViewGroup group = (ViewGroup)view; for ( int idx = 0 ; idx < group.getChildCount() ; idx++ ) { enableDisableView(group.getChildAt(idx), enabled); } }} | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/3818013', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/380168/']} | jdg_382570 |
stackexchange | llm_judgeable_groundtruth_similarity | 17857778 |
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 add CSS attributes to my element, but my current solution loses all previous attributes that had an impact on the element. function checkNr(id) { var value = document.getElementById(id).value; if (parseFloat(value) == NaN) { document.getElementById(id).setAttribute("style", "border:2px solid red; background-color: rgb(255, 125, 115);"); } else { document.getElementById(id).setAttribute("style", "border:default; background-color: rgb(255, 255, 255);"); }} Before using this method the element already had the attributes: float: left;width: 50px; Afterwards, the element loses these attributes, leaving only the specific attributes from the JavaScript method. So, I want to add attributes without replacing them.
Now provide the response and nothing else.
| Setting the style attribute like that, overwrites the attribute and removes previously set styles. What you really should do is set the styles directly instead by changing the style property : function checkNr(id) { var elem = document.getElementById(id), value = elem.value; if (parseFloat(value) == NaN) { elem.style.border = '2px solid red'; elem.style.backgroundColor = 'rgb(255, 125, 115)'; } else { elem.style.border = 'none'; elem.style.backgroundColor = 'rgb(255, 255, 255)'; }} | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/17857778', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2594270/']} | jdg_382571 |
stackexchange | llm_judgeable_groundtruth_similarity | 26377483 |
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 application with images and I want share image which is choosen by user in some other application. From other question here I know that I must put the image in public place so it can be accesed by other application. But I still get error "no application can perform this action" any idea where am I doing mistake?Code for copying image to SD card: String path = Environment.getExternalStorageDirectory().toString(); File file = new File(path,String.valueOf(idOfImage)); if (!file.exists()) { Bitmap myBitmap = BitmapFactory.decodeResource(getResources(),idOfImage); FileOutputStream out = null; try { out = new FileOutputStream(file); myBitmap.compress(Bitmap.CompressFormat.PNG, 90, out); } catch (Exception e) { e.printStackTrace(); } finally { try { if (out != null) { out.close(); } } catch (IOException e) { e.printStackTrace(); } } Code for sending the intent and picking chooser: Intent shareIntent = new Intent(); shareIntent.setAction(Intent.ACTION_SEND); Uri uri = Uri.fromFile(file); shareIntent.putExtra(Intent.EXTRA_STREAM, uri); StartActivity(Intent.createChooser(shareIntent,getResources().getText(R.string.share))); Thanks for answers. EDIT: Works fine when sharingIntent.setType("image/png"); lane added, with Gmail and G+ , but doesnt work with Messengers FB and others.
Now provide the response and nothing else.
| If you don't somehow retain the peripheral object that is delivered to didDiscoverPeripheral then it is released once this delegate method exits and you won't get a connection. I suggest adding a property to track discovered peripherals @property (strong,nonatomic) NSMutableArray *peripherals; initialise this in viewDidLoad or init self.peripherals=[NSMutableArray new]; And then add the peripheral to it in didDiscoverPeripheral -(void) centralManager:(CBCentralManager *)central didDiscoverPeripheral:(CBPeripheral *)peripheral advertisementData:(NSDictionary *)advertisementData RSSI:(NSNumber *)RSSI{ NSLog(@"Discovered peripheral %@",peripheral.identifier.UUIDString); [self.peripherals addObject:peripheral]; [central connectPeripheral:peripheral options:nil];} | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/26377483', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/4116904/']} | jdg_382572 |
stackexchange | llm_judgeable_groundtruth_similarity | 402497 |
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 so-called 'natural unit', it is said that physical quantities are measured in the dimension of 'mass'. For example, $\text{[length]=[mass]}^{-1}$ and so on. In quantum field theory, the dimension of coupling constant is very important because it determines renormalizability of the theory. However, I do not see what exactly the mathematical meaning of 'physical dimension' is. For example, suppose we have self-interaction terms $g_1\cdot \phi\partial^\mu \phi \partial_\mu \phi$ and $g_2 \cdot \phi^4$ , where $\phi$ is a real scalar field, $g_i$ are coupling constants and we assume $4$ dimensional spacetime. Then, it is stated in standard physics books that the scalar field is of mass dimension $1$ and so $g_1$ must be of mass dimension $-1$ and $g_2$ is dimensionless. But, these numbers do not seem to play any 'mathematical' role. To clarify my questions, What forbids me from proclaiming that $\phi$ is dimensionless instead of mass dimension $1$ ? What is the exact difference between a dimensionless coupling constant and a coupling constant of mass dimension $-1$ ? These issues seem very fundamental but always confuse me. Could anyone please provide a precise answer?
Now provide the response and nothing else.
| Mathematically, the concept of a physical dimension is expressed using one-dimensional vector spaces and their tensor products. For example, consider mass.You can add masses together and you know how to multiply a mass by a real number.Thus, masses should form a one-dimensional real vector space $M$ . The same reasoning applies to other physical quantities, like length, time, temperature, etc.Denote the corresponding one-dimensional vector spaces by $L$ , $T$ , etc. When you multiply (say) some mass $m∈M$ and some length $l∈L$ ,the result is $m⊗l∈M⊗L$ .Here $M⊗L$ is another one-dimensional real vector space,which is capable of “storing” physical quantities of dimension mass times length. Multiplicative inverses live in the dual space:if $m∈M$ , then $m^{-1}∈M^*$ , where $\def\Hom{\mathop{\rm Hom}} \def\R{{\bf R}} M^*=\Hom(M,\R)$ .The element $m^{-1}$ is defined as the unique element in $M^*$ such that $m^{-1}(m)=1$ , where $-(-)$ denotes the evaluationof a linear functional on $M$ on an element of $M$ .Observe that $m ⊗ m^{-1} ∈ M⊗M^* ≅ \R$ , where the latter canonical isomorphismsends $(f,m)$ to $f(m)$ , so $m^{-1}$ is indeed the inverse of $m$ . Next, you can also define powers of physical quantities,i.e., $m^t$ , where $m∈M$ is a mass and $t∈\R$ is a real number.This is done using the notion of a density from differential geometry.(The case $\def\C{{\bf C}} t\in\C$ works similarly, but withcomplex one-dimensional vector spaces.)In order to do this, we must make $M$ into an oriented vector space.For a one-dimensional vector space, this simply means thatwe declare one out of the two half-rays in $M∖\{0\}$ to be positive,and denote it by $M_{>0}$ .This makes perfect sense for physical quantities like mass, length, temperature. Once you have an orientation on $M$ ,you can define $\def\Dens{\mathop{\rm Dens}} \Dens_d(M)$ for $d∈\R$ as the one-dimensional (oriented) real vector spacewhose elements are equivalence classes of pairs $(a,m)$ ,where $a∈\R$ , $m∈M_{>0}$ .The equivalence relation is defined as follows: $(a,b⋅m)∼(a b^d,m)$ for any $b∈\R_{>0}$ .The vector space operations are defined as follows: $0=(0,m)$ for some $m∈M_{>0}$ , $-(a,m)=(-a,m)$ , $(a,m)+(a',m)=(a+a',m)$ ,and $s(a,m)=(sa,m)$ .It suffices to add pairs with the samesecond component $m$ because the equivalence relation allows you to change the second component arbitrarily. Once we have defined $\Dens_d(M)$ , given $m∈M_{>0}$ and $d∈\R$ ,we define $m^d∈\Dens_d(M)$ as the equivalence class of the pair $(1,m)$ .It is easy to verify that all the usual laws of arithmetic,like $m^d m^e = m^{d+e}$ , $m^d n^d = (mn)^d$ , etc.,are satisfied, provided that multiplication and reciprocals are interpreted as explained above. Using the power operation operations we just defined,we can now see that the equivalence class of $(a,m)$ is equal to $a⋅m^d$ , where $m∈M_{>0}$ , $m^d∈\Dens_d(M)_{>0}$ ,and $a⋅m^d∈\Dens_d(M)$ .This makes the meaning of the equivalence relation clear. In particular, for $d=-1$ we have a canonical isomorphism $\Dens_{-1}(M)→M^*$ that sends the equivalence class of $(1,m)$ to the element $m^{-1}∈M^*$ defined above,so the two notions of a reciprocal element coincide. If you are dealing with temperature without knowing about the absolute zero,it can be modeled as a one-dimensional real affine space.That is, you can make sense of a linear combination $$a_1 t_1 + a_2 t_2 + a_3 t_3$$ of temperatures $t_1$ , $t_2$ , $t_3$ as long as $a_1+a_2+a_3=1$ ,and you don't need to know about the absolute zero to do this.The calculus of physical quantities can be extendedto one-dimensional real affine spaces without much difficulty. None of the above constructions make any noncanonical choices ofphysical units (such as a unit of mass, for example).Of course, if you do fix such a unit $μ∈M_{>0}$ , you can constructan isomorphism $\R→\Dens_d(M)$ that sends $a∈\R$ to $aμ^d$ ,and the above calculus (including the power operations)is identified with the usual operations on real numbers. In general relativity, we no longer have a single one-dimensionalvector space for length.Instead, we have the tangent bundle ,whose elements model (infinitesimal) displacements.Thus, physical quantities no longer live in a fixed one-dimensionalvector space, but rather are sections of a one-dimensionalvector bundle constructed from the tangent bundle.For example, the volume is an element of the total spaceof the line bundle of 1-densities $\Dens_1(T M)$ ,and the length is now given by the line-bundle of $λ$ -densities $\Dens_λ(T M)$ , where $λ=1/\dim M$ . | {} | {'log_upvote_score': 7, 'links': ['https://mathoverflow.net/questions/402497', 'https://mathoverflow.net', 'https://mathoverflow.net/users/56524/']} | jdg_382573 |
stackexchange | llm_judgeable_groundtruth_similarity | 53445145 |
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 can I make the path /name/int/float be optional. So if I did: http://localhost/Zeref/ it would still work despite not inputting an int or float. And if I did http://localhost/Zeref/1/ It will do just name and the int not the float. So what can I do to make them optional? Code: import flaskwin = flask.Flask(__name__)@win.route("/<name>/<int:ints>/<float:floats>")def web(name, ints, floats): return "Welcome Back: %s Your Int: %d Your Float: %f" % (name, ints, floats)win.run("localhost", 80)
Now provide the response and nothing else.
| Optional parameters are allowed in Flask. You can define multiple rules for same function. Here is the documentation on URL Route Registrations . Updated code: import flaskwin = flask.Flask(__name__)@win.route('/<name>/', defaults={'ints': None, 'floats': None})@win.route('/<name>/<int:ints>/', defaults={'floats': None})@win.route("/<name>/<int:ints>/<float:floats>/")def web(name, ints, floats): if ints!=None and floats!=None: return "Welcome Back: %s, Your Int: %d, Your Float: %f" % (name, ints, floats) elif ints!=None and floats==None: return "Welcome Back: %s, Your Int: %d" % (name, ints) return "Welcome Back: %s" % (name)win.run(debug=True) When chrome or any other web browser requests either of these URLs, Flask will invoke the associated function along with the arguments provided in the url. If no or less arguments are provided then default values of arguments will be used. Screenshots: Three parameters: Two parameters: One parameter: | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/53445145', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/10565111/']} | jdg_382574 |
stackexchange | llm_judgeable_groundtruth_similarity | 2533598 |
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:
What is the limit of $\displaystyle{ \lim \limits_{n \to \infty} \sqrt[n]{\sqrt[2^n]{a}-1}}$ given $a>1$ ? I did some computations and I feel its $\frac{1}{2}$ , i don't know how to prove it I did used Bernoulli inequality
Now provide the response and nothing else.
| Note that$$\lim_{n\to\infty}n\left(\sqrt[n]a-1\right)=\log a\tag{1}.$$This equality comes from $$\lim_{n\to\infty}n\left(\sqrt[n]a-1\right)=\lim_{n\to\infty}\frac{a^\frac1n-1}{\frac1n},$$which is the derivative at $0$ of the function $t\mapsto a^t$. Since $a^t=\exp\bigl(t\log(a)\bigr)$, this derivative is $\log a$. From $(1)$, you can deduce that$$\lim_{n\to\infty}2^n\left(\sqrt[2^n]a-1\right)=\log a\in(0,+\infty).$$But then$$\lim_{n\to\infty}\sqrt[n]{2^n\left(\sqrt[2^n]a-1\right)}=1,$$which means that$$\lim_{n\to\infty}\sqrt[n]{\sqrt[2^n]a-1}=\frac12.$$ | {} | {'log_upvote_score': 5, 'links': ['https://math.stackexchange.com/questions/2533598', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/411780/']} | jdg_382575 |
stackexchange | llm_judgeable_groundtruth_similarity | 22295665 |
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 much is the overhead of smart pointers compared to normal pointers in C++11? In other words, is my code going to be slower if I use smart pointers, and if so, how much slower? Specifically, I'm asking about the C++11 std::shared_ptr and std::unique_ptr . Obviously, the stuff pushed down the stack is going to be larger (at least I think so), because a smart pointer also needs to store its internal state (reference count, etc), the question really is, how much is this going to affect my performance, if at all? For example, I return a smart pointer from a function instead of a normal pointer: std::shared_ptr<const Value> getValue();// versusconst Value *getValue(); Or, for example, when one of my functions accept a smart pointer as parameter instead of a normal pointer: void setValue(std::shared_ptr<const Value> val);// versusvoid setValue(const Value *val);
Now provide the response and nothing else.
| std::unique_ptr has memory overhead only if you provide it with some non-trivial deleter. std::shared_ptr always has memory overhead for reference counter, though it is very small. std::unique_ptr has time overhead only during constructor (if it has to copy the provided deleter and/or null-initialize the pointer) and during destructor (to destroy the owned object). std::shared_ptr has time overhead in constructor (to create the reference counter), in destructor (to decrement the reference counter and possibly destroy the object) and in assignment operator (to increment the reference counter). Due to thread-safety guarantees of std::shared_ptr , these increments/decrements are atomic, thus adding some more overhead. Note that none of them has time overhead in dereferencing (in getting the reference to owned object), while this operation seems to be the most common for pointers. To sum up, there is some overhead, but it shouldn't make the code slow unless you continuously create and destroy smart pointers. | {} | {'log_upvote_score': 9, 'links': ['https://Stackoverflow.com/questions/22295665', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/202919/']} | jdg_382576 |
stackexchange | llm_judgeable_groundtruth_similarity | 2962544 |
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:
Here's what I did: For case 1, 2 and 3, I'm ok now, but for case 4, I still have trouble finding the right way to solve it. My solution to case 4 is theoretically possible, but as for me, I've no idea how to do it. Case 1: Angle between the given plane and the given line is greater than 30 degrees: No solution Case 2: Angle between the given plane and the given line is 0 degree: 2 planes satisfy A line with a direction vector perpendicular to the given line, and is 30 degree to the plane. Case 3: Angle between the given plane and the given line is 30 degree: 1 plane satisfies Reverse the process from case 2. Use the projection of the given line on the plane, find the vector 90 to it that lies on the plane. Case 4: Angle between the given plane and the given line is between 0 and 30 degrees exclusive: 2 planes satisfy Step 1: find the intersection between the plane the and the given line Step 2: use the equation of the plane and the point determined from step 1, find the lines that pass through the point and makes a 30-degree angle to the plane. The equation obtained should describe two conics with their heads pointing perpendicular to the plane. Step 3: Get the equation for the infinite vectors that is perpendicular to the lines from step 2 and lies on the given plane. Step4: Find the solutions to the equation where the cross product of the vectors from step 3 and 4 is perpendicular to the given line.
Now provide the response and nothing else.
| Yes, this is possible, but the proof is not short and simple. From a birds-eye view, the trick is to start by proving double-negation elimination : $$ \neg\neg Q \to Q $$ This requires two instances of axiom 2: $$ (\neg\neg\neg\neg Q \to \neg\neg Q) \to (\neg Q \to \neg\neg\neg Q) \\(\neg Q \to \neg\neg\neg Q) \to (\neg\neg Q \to Q) $$ If we temporarily assume $\neg\neg Q$ , then by axiom 1 we have $\neg\neg\neg\neg Q\to\neg\neg Q$ , and by the two implications above get get $\neg\neg Q\to Q$ . Since we're still assuming $\neg\neg Q$ , we can get $Q$ . Now the deduction theorem applied to this reasoning then gives a proof of $\neg\neg Q\to Q$ without any additional assumptions. To arrive at double-negation introduction , set $Q := \neg P$ . The elimination formula we have just proved is then $$ \neg\neg\neg P \to \neg P $$ and a final appeal to axiom 2 converts this into the desired $$ P \to \neg\neg P $$ Unfolding the deduction theorem (and optimising a bit by hand) gives us this somewhat formidable proof, where several internal application of modus ponens have been omitted: $$ \begin{array}{rll} \\1. & \neg^3P \to (\neg^5 P \to \neg^3 P) & \mathrm{Ax.}1 \\2. & (\neg^5P \to \neg^3P) \to (\neg^2P\to\neg^4P) & \mathrm{Ax.}2 \\3. & \neg^3P \to (\neg^5P \to \neg^3P) \to (\neg^2P\to\neg^4P) & \mathrm{Ax.}1, (2) \\4. & \neg^3P \to (\neg^2P \to \neg^4P) & \mathrm{Ax.}3, (3), (1) \\5. & (\neg^2P \to \neg^4P) \to (\neg^3P\to\neg P) & \mathrm{Ax.}2 \\6. & \neg^3P \to (\neg^2P \to \neg^4P) \to (\neg^3 P\to\neg P) & \mathrm{Ax.}1, (5) \\7. & \neg^3P \to (\neg^3P \to \neg P) & \mathrm{Ax.}3, (6), (4) \\8. & \neg^3P \to \neg^3P & \mathrm{Ax.}1, \mathrm{Ax.}3 \\9. & \neg^3P \to \neg P & \mathrm{Ax.3}, (7), (8) \\10. & P\to \neg\neg P & \mathrm{Ax.2}, (9) \end{array} $$ | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/2962544', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/523130/']} | jdg_382577 |
stackexchange | llm_judgeable_groundtruth_similarity | 83028 |
Below is a question asked on the forum security.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
My goal is to sniff the HTTPS traffic of some digital devices (AppleTV, game consoles, etc.), and decrypt the HTTPS packets in my local network. I cannot figure out a way by using some HTTPS debugging proxy tools like Charles or Fiddler, because they need to have a certificate installed on the device. I don't have access to the file system on the device, I cannot copy certificate. But I can set the proxy of the device to point to my laptop or using my laptop's hotspot.
Now provide the response and nothing else.
| The entire point of SSL is its resistance to eavesdropping by man-in-the-middle attacks like the one you're proposing. If you cannot make the client device trust your self-signed certificate, then your only options are: Intercept an initial HTTP request and never let the communication be upgraded to HTTPS (but this will not work if the if the client explicitly goes to an https://... URL) Pretend to be the server with your own self-signed certificate, and hope that the system making the request naively accepts a self-signed certificate (which is the decision-making equivalent to a user who ignores the browser's stern warnings about a possible MITM attack in progress) Check for susceptibility to known past attacks on SSL (Heartbleed, BEAST, etc.). Note that this option is most likely to be illegal, since it may require an attack on the server (which you don't own) rather than an attack on the client (which you do possibly do own) If you have many trillions of dollars available to you, you may have a few other options: Successfully compromise a worldwide-trusted certificate authority and use their secret signing key to produce forged certificates for your own keypair Purchase or discover a zero-day security vulnerability in a Web client, Web server, or (most preferably) SSL/TLS library used by the client or server Discover a crippling weakness in some underlying cryptographic primitive used by SSL (for example, completely breaking AES might do nicely) Spend trillions of dollars on computer hardware to perform brute force attacks on intercepted encrypted communications If you have unlimited physical access to the device, almost certainly an attack on the device's own trusted certificate store would be easier than an attack on SSL (though it may also be far from easy). | {} | {'log_upvote_score': 6, 'links': ['https://security.stackexchange.com/questions/83028', 'https://security.stackexchange.com', 'https://security.stackexchange.com/users/69612/']} | jdg_382578 |
stackexchange | llm_judgeable_groundtruth_similarity | 15415705 |
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 next template: <div ng-repeat="friend in friends | filter:filterFriendsHandler"> {{friend.name}}</div> and in my controller i have: $scope.filterFriendsHandler = function(friend){ //HERE I WANT TO ACCESS TO FRIEND DOM ELEMENT; to do something like this: //$(friendElement).text('foo');} Thanks
Now provide the response and nothing else.
| You need to use a directive for that <div ng-app="test-app" ng-controller="MyController"> <div ng-repeat="friend in friends" nop> {{friend.title}} </div></div> JS app.directive('nop', function(){ return { link: function(scope, elm){ console.log('eee', elm, arguments); elm.css('color', 'red'); } }}); demo: Fiddle | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/15415705', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/980622/']} | jdg_382579 |
stackexchange | llm_judgeable_groundtruth_similarity | 199615 |
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'm developing some game theory models that involve normal distributions, and am not sure how to solve this probability problem: Suppose there are two normal distributions:$$X_1 \sim N(\mu_1, \sigma^2)$$$$X_2 \sim N(\mu_2, \sigma^2)$$ You know what both distributions are, but that's all you know. I take a draw (call it $s$) from one of the two distributions and show it to you. Given $s$, what is the probability I chose from $X_1$? Thanks for any help! Here's of a picture of two overlapping normal distributions in case it's helpful to have a visual:
Now provide the response and nothing else.
| As Adrian already suggested you need to know the prior probability that $X$ came from each distribution. If $Y$ is an indicator telling us whether or not $X$ came from distribution one and $p_1$ and $p_2$ are the mixing (prior) probabilities then $$P(Y = 1 \mid X = x) = \frac{p_1 f_{X \mid Y=1}(x)}{p_1 f_{X \mid Y=1}(x) + p_2 f_{X \mid Y=0}(x)} .$$ All you've specified are the conditional densities $f_{X \mid Y = 1}$ and $f_{X \mid Y = 0}$ but this isn't enough to calculate the probability. You also need to know something about $p_1$ and $p_2$. | {} | {'log_upvote_score': 4, 'links': ['https://stats.stackexchange.com/questions/199615', 'https://stats.stackexchange.com', 'https://stats.stackexchange.com/users/102815/']} | jdg_382580 |
stackexchange | llm_judgeable_groundtruth_similarity | 2521277 |
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 watched the video and I know the general principles - hot happens even when nobody is subscribed, cold happens "on demand".Also, Publish() converts cold to hot and Defer() converts hot to cold. But still, I feel I am missing the details. Here are some questions I'd like to have answered: Can you give a comprehensive definition for these terms? Does it ever make sense to call Publish on a hot observable or Defer on a cold? What are the aspects of Hot/Cold conversions - do you lose messages, for example? Are there differences between hot and cold definitions for IObservable and IEnumerable? What are the general principles you should take into account when programming for cold or hot? Any other tips on hot/cold observables?
Now provide the response and nothing else.
| From: Anton Moiseev's Book “Angular Development with Typescript, Second Edition.” : Hot and cold observables There are two types of observables : hot and cold. The maindifference is that a cold observable creates a dataproducer for each subscriber , whereas a hot observablecreates a data producer first , and each subscriber gets the data from one producer , starting from the moment of subscription . Let’s compare watching a movie on Netflix to going into a movie theater . Think of yourself as an observer . Anyone who decides to watch Mission: Impossible on Netflix will get the entiremovie, regardless of when they hit the play button. Netflix creates anew producer to stream a movie just for you. This is a coldobservable . If you go to a movie theater and the showtime is 4 p.m., the produceris created at 4 p.m., and the streaming begins. If some people( subscribers ) are late to the show, they miss the beginning of themovie and can only watch it starting from the moment of arrival. Thisis a hot observable . A cold observable starts producing data when some code invokes a subscribe() function on it. For example, your app may declare an observable providing a URL on the server to get certain products. Therequest will be made only when you subscribe to it. If another scriptmakes the same request to the server, it’ll get the same set of data. A hot observable produces data even if no subscribers areinterested in the data. For example, an accelerometer in yoursmartphone produces data about the position of your device, even if noapp subscribes to this data. A server can produce the latest stockprices even if no user is interested in this stock. | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/2521277', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/58463/']} | jdg_382581 |
stackexchange | llm_judgeable_groundtruth_similarity | 2491634 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
#include<stdio.h>#include<conio.h>#define ABC 20#define XYZ 10#define XXX ABC - XYZvoid main(){ int a; a = XXX * 10; printf("\n %d \n", a); getch();} I thought the output should be 100 but when I saw the result I found output as -80. When I put brackets as #define XXX (ABC-XYZ) then I get output as 100 but without brackets I get output as -80.
Now provide the response and nothing else.
| The preprocessor is a dumb beast. It works on a purely textual level, without regard for what it's doing to the code semantically. Let's see what it does in this case: a = XXX * 10; becomes a = ABC - XYZ * 10; which becomes a = 20 - 10 * 10; which is, obviously, -80 . What was probably intended was #define XXX (ABC - XYZ) This is one reason why macros are considered evil. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/2491634', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/223622/']} | jdg_382582 |
stackexchange | llm_judgeable_groundtruth_similarity | 69090 |
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 ran across an infinite series that is allegedly from a Chinese math contest. Evaluate: $\displaystyle\sum_{n=2}^{\infty}(-1)^{n}\ln\left(1-\frac{1}{n(n-1)}\right).$ I thought perhaps this telescoped in some fashion. So, I wrote out $\ln(1/2)-\ln(5/6)+\ln(11/12)-\ln(19/20)+\ln(29/30)-..............$ Separated the positive and negative using log properties: $\ln(1/2)+\ln(11/12)+\ln(29/30)+......=\ln(\frac{1}{2}\cdot \frac{11}{12}\cdot \frac{29}{30}\cdot\cdot\cdot)$ $-(\ln(5/6)+\ln(19/20)+\ln(41/42)+......=-\ln(\frac{5}{6}\cdot \frac{19}{20}\cdot \frac{41}{42}\cdot\cdot\cdot) $ $\ln(\frac{1}{2}\cdot \frac{11}{12}\cdot \frac{29}{30}\cdot\cdot\cdot)-\ln(\frac{5}{6}\cdot \frac{19}{20}\cdot \frac{41}{42}\cdot\cdot\cdot)$ $=\displaystyle \ln\left(\frac{\frac{1}{2}\cdot \frac{11}{12}\cdot \frac{29}{30}\cdot\cdot\cdot}{\frac{5}{6}\cdot \frac{19}{20}\cdot \frac{41}{42}\cdot\cdot\cdot}\right)$ Maybe come up with a general term at the end of the partial sum? The terms in the numerator are $n=2,4,6,....$ and those in the denominator are $n=3,5,7,.....$ $\frac{N(N-1)-1}{N(N-1)}$. But, I always end up with a limit of 1. This then gives $\ln(1)=0$. The series does converge. I managed to do some cancellations, but failed to wrap it up. I thought maybe I was onto something. I suppose I am and not seeing it. What would be a good plan of attack for this one? Since it was in a contest, I assume it can be done. Any thoughts? Thanks very much.
Now provide the response and nothing else.
| Use $ \log\left(1 - \frac{1}{n(n-1)}\right) = \int_0^1 \frac{\mathrm{d} t}{n(1-n)+t}$. Then $$ \begin{eqnarray} \sum_{n=2}^\infty \frac{(-1)^n}{n - n^2 + t} &=& \sum_{n=2}^\infty \frac{2 (-1)^n }{\sqrt{4 t+1}} \left(\frac{1}{2 n+\sqrt{4 t+1}-1}-\frac{1}{2 n-\sqrt{4 t+1}-1}\right) \\&=& \frac{1}{2 \sqrt{4 t+1}} \left( \psi ^{(0)}\left(-\frac{1}{4} \sqrt{4 t+1}-\frac{1}{4}\right)-\psi ^{(0)}\left(\frac{1}{4}-\frac{1}{4} \sqrt{4 t+1}\right) \right) \\ &+& \frac{1}{2 \sqrt{4 t+1}} \left(\psi ^{(0)}\left(\frac{1}{4} \sqrt{4 t+1}+\frac{1}{4}\right) -\psi ^{(0)}\left(\frac{1}{4} \sqrt{4 t+1}-\frac{1}{4}\right)\right)\end{eqnarray}$$The latter comes about from $\sum_{n=1}^\infty \left(\frac{1}{n} - \frac{1}{n+a}\right) = \gamma + \psi^{(0)}(a+1)$, and the summation above was split into summation over even and odd integers. Integrating this expression out produces:$$ \text{log$\Gamma $}\left(\frac{1}{2}-\frac{\phi}{2} \right)-\text{log$\Gamma $}\left(-\frac{1}{2}+\frac{\phi }{2}\right)-\text{log$\Gamma $}\left(-\frac{\phi }{2}\right)+\text{log$\Gamma $}\left(\frac{\phi }{2}\right)+\log (2)$$where $\phi$ is Golden ratio. Integration is trivial as $\frac{\mathrm{d} t}{\sqrt{4 t+1}} = \mathrm{d}\left(\frac{\sqrt{4 t+1}}{2}\right)$, and $\int \psi^{(0)}(u) \mathrm{d} u = \log\Gamma(u) + C$. Numerical check in Mathematica : In[85]:= N[ Log[2] - LogGamma[-GoldenRatio/2] + LogGamma[-(GoldenRatio/2) + 1/2] - LogGamma[GoldenRatio/2 - 1/2] + LogGamma[GoldenRatio/2], 20]Out[85]= -0.56655310975860303045 + 0.*10^-21 IIn[84]:= NSum[(-1)^n Log[1 - 1/(n (n - 1))], {n, 2, \[Infinity]}, WorkingPrecision -> 20]Out[84]= -0.566553109758603 | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/69090', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/13295/']} | jdg_382583 |
stackexchange | llm_judgeable_groundtruth_similarity | 245145 |
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've created a simple C program like so: int main(int argc, char *argv[]) { if (argc != 5) { fputs("Not enough arguments!\n", stderr); exit(EXIT_FAILURE); } And I have my PATH modified in etc/bash.bashrc like so: PATH=.:$PATH I've saved this program as set.c and am compiling it with gcc -o set set.c in the folder ~/Programming/so However, when I call set 2 3 nothing happens. There is no text that appears. Calling ./set 2 3 gives the expected result I've never had a problem with PATH before and which set returns ./set . So it seems the PATH is the correct one. What's is happening?
Now provide the response and nothing else.
| Instead of using which , which doesn't work when you need it most , use type to determine what will run when you type a command: $ which set./set$ type setset is a shell builtin The shell always looks for builtins before searching the $PATH , so setting $PATH doesn't help here. It would be best to rename your executable to something else, but if your assignment requires the program to be named set , you can use a shell function: $ function set { ./set; }$ type setset is a functionset (){ ./set} (That works in bash , but other shells like ksh may not allow it. See mikeserv's answer for a more portable solution.) Now typing set will run the function named "set", which executes ./set . GNU bash looks for functions before looking for builtins, and it looks for builtins before searching the $PATH . The section named "COMMAND EXECUTION" in the bash man page gives more information on this. See also the documentation on builtin and command : help builtin and help command . | {} | {'log_upvote_score': 6, 'links': ['https://unix.stackexchange.com/questions/245145', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/137641/']} | jdg_382584 |
stackexchange | llm_judgeable_groundtruth_similarity | 200345 |
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:
Is the mean sensitive to the presence of outliers? I initially thought it wasn't, because a small amount of observations shouldn't have much impact, but was told that since those observations have very different values from the rest, they have a considerable impact. Thoughts?
Now provide the response and nothing else.
| Consider what would happen if you wanted to take the mean of some numbers, but you dragged one of them off toward infinity. Sure, at first it wouldn't have a huge impact on the mean, but the farther you drag it off, the more your mean changes. Every number has a (proportionally) small contribution to the mean, but they do all contribute. So if one number is really different than the others, it can still have a big influence. This idea of dragging values off toward infinity and seeing how the estimator behaves is formalized by the breakdown point : the proportion of data that can get arbitrarily large before the estimator also becomes arbitrarily large. The mean has a breakdown point of 0, because it only takes 1 bad data point to make the whole estimator bad (this is actually the asymptotic breakdown point, the finite sample breakdown point is 1/N). On the other hand, the median has breakdown point 0.5 because it doesn't care about how strange data gets, as long as the middle point doesn't change. You can take half of the data and make it arbitrarily large and the median shrugs it off. You can even construct an estimator with whatever breakdown point you want (between 0 and 0.5) by 'trimming' the mean by that percentage--throwing away some of the data before computing the mean. So, what does this mean for actually doing work? Is the mean just a terrible idea? Well, like everything else in life, it depends. If you desperately need to protect yourself against outliers, yeah, the mean probably isn't for you. But the median pays a price of losing a lot of potentially helpful information to get that high breakdown point. If you're interested in reading more about it, here's a set of lecture notes that really helped me when I was learning about robust statistics. http://www.stat.umn.edu/geyer/5601/notes/break.pdf | {} | {'log_upvote_score': 4, 'links': ['https://stats.stackexchange.com/questions/200345', 'https://stats.stackexchange.com', 'https://stats.stackexchange.com/users/107717/']} | jdg_382585 |
stackexchange | llm_judgeable_groundtruth_similarity | 25290394 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
While looking over some code, I ran into the following: .h file class ExampleClass{public: // methods, etcprivate: class AnotherExampleClass* ptrToClass;} .cpp file class AnotherExampleClass{ // methods, etc}// AnotherExampleClass and ExampleClass implemented Is this a pattern or something beneficial when working in c++? Since the class is not broken out into another file, does this work flow promote faster compilation times? or is this just the style this developer?
Now provide the response and nothing else.
| This is variously known as the pImpl Idiom , Cheshire cat technique, or Compilation firewall. Benefits: Changing private member variables of a class does not require recompiling classes that depend on it, thus make times are faster, and the FragileBinaryInterfaceProblem is reduced. The header file does not need to #include classes that are used 'by value' in private member variables, thus compile times are faster. This is sorta like the way SmallTalk automatically handles classes... more pure encapsulation. Drawbacks: More work for the implementor. Doesn't work for 'protected' members where access by subclasses is required. Somewhat harder to read code, since some information is no longer in the header file. Run-time performance is slightly compromised due to the pointer indirection, especially if function calls are virtual (branch prediction for indirect branches is generally poor). Herb Sutter's "Exceptional C++" books also go into useful detail on the appropriate usage of this technique. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/25290394', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/242924/']} | jdg_382586 |
stackexchange | llm_judgeable_groundtruth_similarity | 5921 |
Below is a question asked on the forum chemistry.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I was taking a chemistry test and I encountered the following question: How many electrons can an orbital of type f hold? A. 6 B. 10 C. 2 D. 14 E. 1 Since there can be [-ℓ, ℓ] orientations and since the orbital type f has ℓ = 3, we should have 7 possible orientations with 2 spins, so ${7 \times 2 = 14}$, so I thought the correct answer was D (14). However, I got it wrong and the correct answer is marked as C (2). Is it an error in the test, or am I missing something?
Now provide the response and nothing else.
| You're correct that there are seven possible spatial orientations for an f-type orbital, and hence seven possible orbitals in one f-type sub-shell. However, the question specifically asks for the maximum number of electrons in one such orbital, and any single atomic orbital, regardless of the sub-shell type specified by $l$, can only hold two electrons. This is by virtue of the Pauli exclusion principle. Fourteen would be the maximum number of electrons across an entire f-type sub-shell, but the question only asks about one orbital. | {} | {'log_upvote_score': 4, 'links': ['https://chemistry.stackexchange.com/questions/5921', 'https://chemistry.stackexchange.com', 'https://chemistry.stackexchange.com/users/2162/']} | jdg_382587 |
stackexchange | llm_judgeable_groundtruth_similarity | 26454160 |
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 updated my OS to Yosemite and the only issue I have is that my localhost is not working anymore. Please excuse if the questions sounds dumb but I have limited knowledge about servers. with Mavericks I was able to use localhost and customdomain.dev right after a system start. Also my MySQL server has been started without any actions Now Google Chrome throws an ERR_CONNECTION_REFUSED error when using localhost. I run apachectl configtest which returns httpd: Syntax error on line 58 of /private/etc/apache2/httpd.conf: Cannot load libexec/apache2/mod_authn_default.so into server: dlopen(/usr/libexec/apache2/mod_authn_default.so, 10): image not found if I comment out this line it continues with other modules. When I comment out all modules which causes this syntax error I get AH00526: Syntax error on line 131 of /private/etc/apache2/httpd.conf:Invalid command 'User', perhaps misspelled or defined by a module not included in the server configuration I'm using the httpd.conf file from Mavericks (where everything worked fine) I have no idea what I should do next
Now provide the response and nothing else.
| Did you retain your original httpd.conf from before the upgrade? You may have to edit the modules in your httpd.conf I found that an Apache upgrade came along with Yosemite. Apparently there are several authentication-related changes from Apache 2.2 to 2.4. I had to run sudo apachectl configtest repeatedly to display which modules to remove. Then, I had to add some modules. My modules look like this now: LoadModule authn_file_module libexec/apache2/mod_authn_file.soLoadModule authn_dbm_module libexec/apache2/mod_authn_dbm.soLoadModule authn_anon_module libexec/apache2/mod_authn_anon.soLoadModule authn_dbd_module libexec/apache2/mod_authn_dbd.so#LoadModule authn_default_module libexec/apache2/mod_authn_default.soLoadModule authn_core_module libexec/apache2/mod_authn_core.soLoadModule authz_host_module libexec/apache2/mod_authz_host.soLoadModule authz_groupfile_module libexec/apache2/mod_authz_groupfile.soLoadModule authz_user_module libexec/apache2/mod_authz_user.soLoadModule authz_dbm_module libexec/apache2/mod_authz_dbm.soLoadModule authz_owner_module libexec/apache2/mod_authz_owner.so#LoadModule authz_default_module libexec/apache2/mod_authz_default.soLoadModule authz_core_module libexec/apache2/mod_authz_core.soLoadModule auth_basic_module libexec/apache2/mod_auth_basic.soLoadModule auth_digest_module libexec/apache2/mod_auth_digest.soLoadModule cache_module libexec/apache2/mod_cache.so#LoadModule disk_cache_module libexec/apache2/mod_disk_cache.so#LoadModule mem_cache_module libexec/apache2/mod_mem_cache.soLoadModule dbd_module libexec/apache2/mod_dbd.soLoadModule dumpio_module libexec/apache2/mod_dumpio.soLoadModule reqtimeout_module libexec/apache2/mod_reqtimeout.soLoadModule ext_filter_module libexec/apache2/mod_ext_filter.soLoadModule include_module libexec/apache2/mod_include.soLoadModule filter_module libexec/apache2/mod_filter.soLoadModule substitute_module libexec/apache2/mod_substitute.soLoadModule deflate_module libexec/apache2/mod_deflate.soLoadModule log_config_module libexec/apache2/mod_log_config.soLoadModule log_forensic_module libexec/apache2/mod_log_forensic.soLoadModule logio_module libexec/apache2/mod_logio.soLoadModule env_module libexec/apache2/mod_env.soLoadModule mime_magic_module libexec/apache2/mod_mime_magic.so#LoadModule cern_meta_module libexec/apache2/mod_cern_meta.soLoadModule expires_module libexec/apache2/mod_expires.soLoadModule headers_module libexec/apache2/mod_headers.so#LoadModule ident_module libexec/apache2/mod_ident.soLoadModule usertrack_module libexec/apache2/mod_usertrack.so#LoadModule unique_id_module libexec/apache2/mod_unique_id.soLoadModule setenvif_module libexec/apache2/mod_setenvif.soLoadModule version_module libexec/apache2/mod_version.soLoadModule proxy_module libexec/apache2/mod_proxy.soLoadModule proxy_connect_module libexec/apache2/mod_proxy_connect.soLoadModule proxy_ftp_module libexec/apache2/mod_proxy_ftp.soLoadModule proxy_http_module libexec/apache2/mod_proxy_http.soLoadModule proxy_scgi_module libexec/apache2/mod_proxy_scgi.soLoadModule proxy_ajp_module libexec/apache2/mod_proxy_ajp.so#LoadModule proxy_balancer_module libexec/apache2/mod_proxy_balancer.soLoadModule ssl_module libexec/apache2/mod_ssl.soLoadModule mime_module libexec/apache2/mod_mime.soLoadModule dav_module libexec/apache2/mod_dav.soLoadModule status_module libexec/apache2/mod_status.soLoadModule autoindex_module libexec/apache2/mod_autoindex.soLoadModule asis_module libexec/apache2/mod_asis.soLoadModule info_module libexec/apache2/mod_info.soLoadModule cgi_module libexec/apache2/mod_cgi.soLoadModule dav_fs_module libexec/apache2/mod_dav_fs.soLoadModule vhost_alias_module libexec/apache2/mod_vhost_alias.soLoadModule negotiation_module libexec/apache2/mod_negotiation.soLoadModule dir_module libexec/apache2/mod_dir.soLoadModule imagemap_module libexec/apache2/mod_imagemap.soLoadModule actions_module libexec/apache2/mod_actions.soLoadModule speling_module libexec/apache2/mod_speling.soLoadModule userdir_module libexec/apache2/mod_userdir.soLoadModule alias_module libexec/apache2/mod_alias.soLoadModule rewrite_module libexec/apache2/mod_rewrite.so#LoadModule perl_module libexec/apache2/mod_perl.so#LoadModule php5_module libexec/apache2/libphp5.soLoadModule unixd_module libexec/apache2/mod_unixd.soLoadModule access_compat_module libexec/apache2/mod_access_compat.soLoadModule php5_module /usr/local/opt/php56/libexec/apache2/libphp5.soLoadModule hfs_apple_module libexec/apache2/mod_hfs_apple.so You'll see that I commented out a few. There are a few new ones. The two _core_ ones, unixd_module , and access_compat_module are new. Don't mind the strange looking PHP module. That's from Homebrew's PHP. I also had to remove the LockFile directive in httpd-mpm.conf . And the NameVirtualHost directive in httpd-vhosts.conf . I hope this helps. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/26454160', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/454979/']} | jdg_382588 |
stackexchange | llm_judgeable_groundtruth_similarity | 464593 |
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:
$$y = \frac{1}{4} x^2 - \frac{1}{2} \ln x$$ $$\int_1^{2e} \sqrt{1 + (y')^2}$$ $$y' = \frac{x}{2} - \frac{1}{2x}$$ $$y' = \frac{2x^2-1}{2x}$$ $$\left(\frac{2x^2-1}{2x}\right)^2$$ $$\frac{4x^4-4x^2+1}{4x^2}$$ $$\int_1^{2e} \sqrt{1 + \frac{4x^4-4x^2+1}{4x^2} }$$ The 1 cancels out the negative term in the numerator $$\int_1^{2e} \sqrt{ \frac{4x^4+1}{4x^2} }$$ So now if i have done this right I have now idea how to integrate this, subsitution doesn't seem to help. What is the trick here?
Now provide the response and nothing else.
| $$1+y'^2=1+\frac14\left(x^2-2+\frac1{x^2}\right)=\frac14\left(x+\frac1x\right)^2\implies$$ $$\int\limits_1^{2e}\sqrt{1+y'^2}dx=\frac12\int\limits_1^{2e}\left(x+\frac1x\right)dx=\ldots$$ | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/464593', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/85142/']} | jdg_382589 |
stackexchange | llm_judgeable_groundtruth_similarity | 168089 |
Below is a question asked on the forum security.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
First of all I am a web developer and not a security expert. I have read lots of articles about the difference between HTTPS and HTTP , including this site. The basic idea I got from them is, when using HTTPS all things are encrypted on the client side and then sent to the server. (Please correct me if I am wrong) So even our network admin or other person in the network can't get anything. When I use my laptop at home (trusted network) , is there any advantage of using HTTPS over HTTP ?
Now provide the response and nothing else.
| TLS provides three things: Confidentiality: that nobody can see the traffic between you and facebook.com (including the guy at the next table at Starbucks, your ISP, some sketchy network equipment in the datacentre COUGH NSA , nobody). Integrity: that nobody is modifying the messages as they travel between you and facebook.com (this is separate from Confidentiality because some kinds of attacks allow you to modify the message in a malicious way even if you don't know what the messages are). Authentication: that you are talking to the authentic facebook.com server, not a spoofed version of it. The basic idea what I got from them is, when using https all things are encrypted in client side and then sent it to the server. (Please correct me if I am wrong) That covers the confidentiality and integrity parts, but you're missing the authentication part: To prove that you're not talking to a spoofed web server. Say I set up a phishing version of Facebook and I somehow hack into your home router (easy) or ISP (harder) so that when you type facebook.com it resolves to my IP address instead of the real one. I've created an exact copy of the login screen you expect and you'll enter your username and password. Muahaha! Now I have your username and password. How does HTTPS prevent this? Answer: with Certificates: If we open up the certificate in my browser's Dev Tools > Security, we'll see this: DigiCert is what's called a Publicly-trusted Certificate Authority (CA) . In fact, DigiCert is one of the CAs that your browser inherently trusts because its "root certificate" is embedded into your browser's source code. You can see the full list of trusted root CAs by digging around in browser Settings and looking for "Certificates" or "Trusted Roots" or something. So, your browser inherently trusts DigiCert, and, through this certificate, DigiCert has certified that the server you are talking to is the real facebook.com (because it has the private key that matches the certificate). You get the green padlock and you know that everything is good. Just for fun, let's make a fake facebook.com . I added this line to my hosts file so that any time I type facebook.com it will redirect to google.com 's IP address: 209.85.147.138 facebook.com Google, what'cha doing trying to steal my facebook password?? Thank goodness HTTPS is here to protect me! My browser is super unhappy because the certificate it was presented (for google.com ) doesn't match the URL it requested ( facebook.com ). Thanks HTTPS! | {} | {'log_upvote_score': 8, 'links': ['https://security.stackexchange.com/questions/168089', 'https://security.stackexchange.com', 'https://security.stackexchange.com/users/156934/']} | jdg_382590 |
stackexchange | llm_judgeable_groundtruth_similarity | 692540 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
What are some examples of where you would use generics in C#/VB.NET and why would you want to use generics?
Now provide the response and nothing else.
| Simply, you declare a type or method with extra tags to indicate the generic bits: class Foo<T> { public Foo(T value) { Value = value; } public T Value {get;private set;}} The above defines a generic type Foo "of T ", where the T is provided by the caller. By convention, generic type arguments start with T. If there is only one, T is fine - otherwise name them all usefully: TSource , TValue , TListType etc Unlike C++ templates, .NET generics are provided by the runtime (not compiler tricks). For example: Foo<int> foo = new Foo<int>(27); All T s have been replaced with int in the above. If necessary, you can restrict generic arguments with constraints: class Foo<T> where T : struct {} Now Foo<string> will refuse to compile - as string is not a struct (value-type). Valid constraints are: T : class // reference-type (class/interface/delegate)T : struct // value-type except Nullable<T>T : new() // has a public parameterless constructorT : SomeClass // is SomeClass or inherited from SomeClassT : ISomeInterface // implements ISomeInterface Constraints can also involve other generic type arguments, for example: T : IComparable<T> // or another type argument You can have as many generic arguments as you need: public struct KeyValuePair<TKey,TValue> {...} Other things to note: static members etc are defined per generic type combination - so a static field on Foo<int> is separate to that on Foo<float> . methods can be generic too - try to avoid using the same names as the class uses, as you won't be able to disambiguate nested types inherit the generic types from their parents for example: class Foo<T> { class Bar<TInner> {} // is effectively Bar<T,TInner>, for the outer T} | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/692540', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/83538/']} | jdg_382591 |
stackexchange | llm_judgeable_groundtruth_similarity | 21262424 |
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 can I do a cumulative sum over a vector (like cumsum ), but bounded so that the summation never goes below a lower bound or above an upper bound? The standard cumsum function would result in the following. foo <- c(100, -200, 400, 200)cumsum(foo)# [1] 100 -100 300 500 I am looking for something as efficient as the base cumsum function. I would expect the output to look like the following. cumsum.bounded(foo, lower.bound = 0, upper.bound = 500)# [1] 100 0 400 500 Thanks
Now provide the response and nothing else.
| As mentioned in the comments, Rcpp is a good way to go. cumsumBounded.cpp : #include <Rcpp.h>using namespace Rcpp;// [[Rcpp::export]] NumericVector cumsumBounded(NumericVector x, double low, double high) { NumericVector res(x.size()); double acc = 0; for (int i=0; i < x.size(); ++i) { acc += x[i]; if (acc < low) acc = low; else if (acc > high) acc = high; res[i] = acc; } return res;} Compile and use new function: library(Rcpp)sourceCpp(file="cumsumBounded.cpp")foo <- c(100, -200, 400, 200)cumsumBounded(foo, 0, 500)# [1] 100 0 400 500 | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/21262424', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2247046/']} | jdg_382592 |
stackexchange | llm_judgeable_groundtruth_similarity | 27524472 |
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 list of data.frame's that I would like to output to their own worksheets in excel. I can easily save a single data frame to it's own excel file but I'm not sure how to save multiple data frames to the their own worksheet within the same excel file. library(xlsx)write.xlsx(sortedTable[1], "c:/mydata.xlsx")
Now provide the response and nothing else.
| Specify sheet name for each list element. library(xlsx)file <- paste("usarrests.xlsx", sep = "")write.xlsx(USArrests, file, sheetName = "Sheet1") write.xlsx(USArrests, file, sheetName = "Sheet2", append = TRUE) Second approach as suggested by @flodel, would be to use addDataFrame . This is more or less an example from the help page of the said function. file <- paste("usarrests.xlsx", sep="")wb <- createWorkbook()sheet1 <- createSheet(wb, sheetName = "Sheet1")sheet2 <- createSheet(wb, sheetName = "Sheet2")addDataFrame(USArrests, sheet = sheet1)addDataFrame(USArrests * 2, sheet = sheet2)saveWorkbook(wb, file = file) Assuming you have a list of data.frames and a list of sheet names, you can use them pair-wise. wb <- createWorkbook()datas <- list(USArrests, USArrests * 2)sheetnames <- paste0("Sheet", seq_along(datas)) # or names(datas) if providedsheets <- lapply(sheetnames, createSheet, wb = wb)void <- Map(addDataFrame, datas, sheets)saveWorkbook(wb, file = file) | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/27524472', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2092359/']} | jdg_382593 |
stackexchange | llm_judgeable_groundtruth_similarity | 1475083 |
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:
$T(n)$ is $n^{th}$ triangular number, where $T\left(n\right)=\frac{n^2+n}{2}$ And from other sources I know the $n^{th}$ tetrahedral number is $G\left(x\right)=\sum _{n=1}^xT\left(n\right)=\frac{\left(x^2+x\right)\left(x+2\right)}{6}$ I also happen to know that the formula for the volume of a tetrahedron is: $V=\frac{1}{2}Ah$, where $A$ is the area of the triangular base and $h$ is the height. If I sat down one day not knowing the formula for $G(x)$ and wanted to create a function to find the $n^{th}$ tetrahedral number, how do I derive it? I've seen proofs. I want to know how the proof authors arrived at that formula in the first place.
Now provide the response and nothing else.
| In general, if $f(n)$ is a polynomial with degree $k$, and if $$\sum_{x=1}^n f(x) = g(n)$$ then $g(n)$ must be a polynomial with degree $k+1$. This means that since triangular numbers are given by a polynomial of degree $2$, tetrahedral numbers must be given by a polynomial of degree $3$. Let $a,b,c,d \in \mathbb{R}$ such that the $n^\text{th}$ tetrahedral number $G(n)$ is given by $$an^3 + bn^2 + cn + d$$ We know immediately that $d=0$ because $G(0)=0$ (the empty sum ). Now we can simply list out any three tetrahedral numbers to find the general formula. Let's use the first three. \begin{align*}G(1) \,&=\, T(1) = 1 \\\\G(2) \,&=\,T(1) + T(2) = 1 + 3 \\\\G(3) \,&=\,T(1) + T(2) + T(3) = 1 + 3 + 6 \\\end{align*} Rewriting, we get these equations involving the coefficients: \begin{align*}1 &= a + b + c\\\\4 &= 8a + 4b + 2c\\\\10 &= 27a + 9b + 3c\\\end{align*} Three linear equations, three variables. While it's a bit tedious to do the row reduction, it's definitely one way to derive the formula. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/1475083', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/272957/']} | jdg_382594 |
stackexchange | llm_judgeable_groundtruth_similarity | 16356810 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Why does this code give a KeyError ? output_format = """{ "File": "{filename}", "Success": {success}, "ErrorMessage": "{error_msg}", "LogIdentifier": "{log_identifier}" }"""print output_format.format(filename='My_file_name', success=True, error_msg='', log_identifier='123') Error message: KeyError: ' "File"'
Now provide the response and nothing else.
| You need to double the outer braces; otherwise Python thinks { "File".. is a reference too: output_format = '{{ "File": "{filename}", "Success": {success}, "ErrorMessage": "{error_msg}", "LogIdentifier": "{log_identifier}" }}' Result: >>> print output_format.format(filename='My_file_name',... success=True,... error_msg='',... log_identifier='123'){ "File": "My_file_name", "Success": True, "ErrorMessage": "", "LogIdentifier": "123" } If, indicentally, you are producing JSON output, you'd be better off using the json module : >>> import json>>> print json.dumps({'File': 'My_file_name',... 'Success': True,... 'ErrorMessage': '',... 'LogIdentifier': '123'}){"LogIdentifier": "123", "ErrorMessage": "", "Success": true, "File": "My_file_name"} Note the lowercase true in the output, as required by the JSON standard. | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/16356810', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/879896/']} | jdg_382595 |
stackexchange | llm_judgeable_groundtruth_similarity | 15108670 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
For example, if i have this: <input type='text' onkeydown='doSomething()' /><script> function doSomething() { // ? }</script> i need to get the keyCode/character pressed in cross-browser/os way.. how to do it? i've tried about this ~6 years ago and as i remember that time, it was not easy, sometimes i must pass event or something to get it work on opera or IE cmiiw
Now provide the response and nothing else.
| You're close, but the issue with your code is you're executing doSomething() in response to keyDown events... let's look closely — you're executing doSomething without passing any arguments in . You're also not naming/accepting arguments, even if you did pass them. A few quick tweaks to your code and you're all set: // Notice an `event` argument, containing the important datafunction doSomething(event) { console.log('****** doSomething'); console.log('event.keyCode: ', event.keyCode); console.log('event.which: ', event.which); console.log('event.key: ', event.key); console.log('event.code: ', event.code);} <!-- Notice: We pass the key `event` object into doSomething --><input type='text' onkeydown='doSomething(event)' placeholder="Type here..." /> How to determine what key was pressed I'm confused on this too, but let's review the options. Get ready for some 1995-esque browser differences! First, keep in mind that while the end goal may be to determine what key was pressed, different methods require different steps to arrive at that. An event can either be a "system and implementation dependent numerical code", a Unicode char value, the Ascii value, or the actual key name ("ArrowUp"). event.key ( TL;DR: Try to use this ) According to MDN KeyboardEvent.key Documentation , event.key is the recommended way if you're looking for the non-deprecated, "future-forward" way. Documentation is under heavy modification though, so details are sparse on MDN. Looking at the caniuse.com support table for event.key , there's no support below IE11 or on Safari at all (as of Jan 2017). That may already be a deal-breaker, so let's keep looking. event.keyCode I've always used event.keyCode , which MDN says is now deprecated and comes with this warning: You should avoid using this if possible; it's been deprecated for some time. Instead, you should use KeyboardEvent.code , if it's implemented. Unfortunately, some browsers still don't have it, so you'll have to be careful to make sure you use one which is supported on all target browsers. Google Chrome and Safari have implemented KeyboardEvent.keyIdentifier , which was defined in a draft specification but not the final spec. Alright, fair enough — there's enough differences between browsers and subtle differences between keydown and keypress events ( not the same thing! ) to make this not worth using any more. RIP keyCode , it's been real! event.which From MDN docs : The numeric code for a particular key pressed, depending on whether an alphanumeric or non-alphanumeric key was pressed. Please see KeyboardEvent.charCode** and KeyboardEvent.keyCode for more details. Another one in the process of deprecation — "This feature has been removed from the Web standards. Though some browsers may still support it, it is in the process of being dropped." Ok, well keyCode we already know is deprecated too, so what's charCode about? event.charCode This returns the Unicode char code for a keypress event... and we get another warning from MDN : Do not use this property anymore, it is deprecated. Use KeyboardEvent.key instead. Starting to chase our own tails here, KeyboardEvent.key is the future-forward approach, but not yet adequately supported... it also returns 0 all the time for keydown events, you must listen to keypress events for this to be valuable. event.code The last option seems promising... event.code docs from MDN : represents a physical key on the keyboard (as opposed to the character generated by pressing the key). In other words, this property returns a value which isn't altered by keyboard layout or the state of the modifier keys. This is handy because we get things like ShiftRight versus ShiftLeft , useful for game development and very specific interactions. There's a great chart at the bottom of the docs for all code options. The catch: not very good support yet . Nothing on IE, iOS Safari, Android, or Opera. So... what should I use? TBH I don't think there's a one-size-fits all solution. The current landscape seems to require some degree of polyfilling, or at least supporting the old event.keyCode and event.which properties as fallbacks for where event.key and event.code can't be used. For production projects, we just need to consider the browser and device support requirements and go from there. Shift/Ctrl/Command/Windows/Etc There's a few extra properties to check if you care about other keys pressed in combination with the original key: event.altKey event.ctrlKey event.metaKey event.shiftKey Handy Tool: keycode.info An invaluable tool for quickly figuring out what keyCode you need to write logic around is http://keycode.info/ (created by the v. cool Wes Bos ) | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/15108670', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1620210/']} | jdg_382596 |
stackexchange | llm_judgeable_groundtruth_similarity | 15417410 |
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 need to render UIBezierPaths without anti-aliasing and then save them as PNG to retain the full pixel representations (for example, not let JPEG muck the image up). I've tried calling the CG functions below just before stroking the UIBezierPaths, but it seems none have any effect on the resultant rendered image. The paths are still rendered with anti-aliasing (i.e. smoothed). CGContextSetShouldAntialias(c, NO);CGContextSetAllowsAntialiasing(c, NO);CGContextSetInterpolationQuality(c, kCGInterpolationNone); Any hits would be greatly appreciated.
Now provide the response and nothing else.
| When I use those options, it turns off antialiasing. On the left is with the default options. On the right, with your options. This is easy to control if you're using a UIView subclass. This is my drawRect : - (void)drawRect:(CGRect)rect{ CGContextRef context = UIGraphicsGetCurrentContext(); CGContextSetShouldAntialias(context, NO); [[UIColor redColor] setStroke]; UIBezierPath *path = [self myPath]; [path stroke];} And to capture the screen, from How to take a screenshot programmatically - (void)captureScreen{ if ([[UIScreen mainScreen] respondsToSelector:@selector(scale)]) UIGraphicsBeginImageContextWithOptions(self.window.bounds.size, NO, [UIScreen mainScreen].scale); else UIGraphicsBeginImageContext(self.window.bounds.size); [self.window.layer renderInContext:UIGraphicsGetCurrentContext()]; UIImage *image = UIGraphicsGetImageFromCurrentImageContext(); UIGraphicsEndImageContext(); NSData *data = UIImagePNGRepresentation(image); [data writeToFile:[self screenShotFilename] atomically:YES];} If you're using a CAShapeLayer , then I don't think you can control the antialiasing on screen, because as the documentation says : The shape will be drawn antialiased, and whenever possible it will be mapped into screen space before being rasterized to preserve resolution independence. However, certain kinds of image processing operations, such as CoreImage filters, applied to the layer or its ancestors may force rasterization in a local coordinate space. But, regardless of the antialiasing on screen, if you want to have your snapshot of the screen not be antialiased, you can insert your CGContextSetShouldAntialias into the captureScreen routine: - (void)captureScreen{ if ([[UIScreen mainScreen] respondsToSelector:@selector(scale)]) UIGraphicsBeginImageContextWithOptions(self.window.bounds.size, NO, [UIScreen mainScreen].scale); else UIGraphicsBeginImageContext(self.window.bounds.size); CGContextRef context = UIGraphicsGetCurrentContext(); CGContextSetShouldAntialias(context, NO); [self.window.layer renderInContext:context]; UIImage *image = UIGraphicsGetImageFromCurrentImageContext(); UIGraphicsEndImageContext(); NSData * data = UIImagePNGRepresentation(image); [data writeToFile:[self screenShotFilename] atomically:YES];} | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/15417410', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1691820/']} | jdg_382597 |
stackexchange | llm_judgeable_groundtruth_similarity | 344245 |
Below is a question asked on the forum mathoverflow.net. Provide a good and informational response to it like a helpful human would.
Question:
Background The fact that there is no suborder of $\mathbb R$ which is of type $\omega_1$ suggests (to me) that the continuum $c$ cannot be very far from $\omega_1$ : How could $c$ be far away from $\omega_1$ if there is no room for an order embedding of $\omega_1$ in $\mathbb R$ ? Of course, this fact is a consequence of the separability of $\mathbb R$ (which is itself an amazing fact: How can continuum many aligned irrationals be separated by only countably many rationals?) From the idea that the continuum cannot be very far from $\omega_1$ because there is no room in $\mathbb R$ to embed $\omega_1$ , one can easily formulate an axiom implying $CH$ : Preliminary definition Let $\kappa$ be an infinite cardinal and $L$ be a total order. We say that $L$ is $\kappa$ -unbounded if $|L|=\kappa$ and for every $a\in L$ , we have that $|\left\{x\in L : a < x\right\}|=\kappa$ . The axiom If $\kappa$ and $\lambda$ are infinite cardinals, $\lambda<\kappa$ , and $L$ is a $\kappa$ -unbounded total order, then there is an order embedding $f: \lambda\rightarrow L$ (in other words, there is a suborder of $L$ of type $\lambda$ ). I have not double-checked every detail, but I am convinced that this axiom easily implies $GCH$ for at least all strong limit cardinals. In particular, it implies $CH$ . Question Is the above axiom consistent with $ZFC$ ? Maybe there is an easy counterexample, but I have not found one. I know that this is related to the dense set problem as presented in Baumgartner, J., Almost disjoint sets, the dense set problem and the partition calculus . EDIT In view of Goldstern's counterexample, here is a modification of the axiom that might be consistent with ZFC: Assume that $\kappa$ and $\lambda$ are infinite cardinals, $\lambda<\kappa$ , $L$ is a $\kappa$ -unbounded total order and that $L^*$ (the reverse order) is also $\kappa$ -unbounded. Then there is an order embedding $f: \lambda\rightarrow L$ or an order embedding $g: \lambda^*\rightarrow L$ (in other words, there is a suborder of $L$ of type $\lambda$ or of type $\lambda^*$ ). This still implies $CH$ and the given counterexamples do not apply.
Now provide the response and nothing else.
| Your axiom is inconsistent. (Or perhaps I have misunderstood it.) Let $L_n:= \aleph_n$ with the reverse order, and let $L:= L_1 + L_2 + \cdots$ (horizontal sum); equivalently, let $L$ be the lexicographic order on $\bigcup_k \{k\}\times L_k$ . Then $L$ is $\aleph_\omega$ -unbounded, yet there is no order-preserving embedding of $\omega_1$ into $L$ : (EDITED to simplify:) Every well-ordered subset of $L$ is finite in each $L_n$ , hence at most countable. | {} | {'log_upvote_score': 4, 'links': ['https://mathoverflow.net/questions/344245', 'https://mathoverflow.net', 'https://mathoverflow.net/users/9825/']} | jdg_382598 |
stackexchange | llm_judgeable_groundtruth_similarity | 26016770 |
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 installing android SDK to create an automated build server. I got into a problem where many Gradle-based Android projects I manage rely on different build tools version. Some of the projects still requiring old build-tools version (e.g. v19.1.0). My android-sdk package was downloaded when build-tools version 20 has just released, so that's the only version available to download via android update sdk -u --filter build-tools . I have tried to invoke android update sdk -u --filter build-tools-19.1.0 but it didn't work. Is there an easy way to install old version of Android build tools from command line? Note: installing via GUI is not possible
Now provide the response and nothing else.
| Assuming you have downloaded the Android SDK for linux, you have two options to update from command line. Download using android tool from the sdk Instead of running the android sdk manager with a GUI, you also have an option to run in headless mode. You just need to specify -u (or --no-ui ) flag. To list packages available for installation or upgrade: $ cd android-sdk-linux$ ./tools/android list sdk --allRefresh Sources: (...) Fetching URL: https://dl.google.com/android/repository/repository-11.xml (...)Packages available for installation or update: 166 1- Android SDK Tools, revision 24.4.1 2- Android SDK Tools, revision 25.0.9 rc10 3- Android SDK Platform-tools, revision 23.1 4- Android SDK Platform-tools, revision 24 rc1 5- Android SDK Build-tools, revision 24 rc1 6- Android SDK Build-tools, revision 23.0.2 7- Android SDK Build-tools, revision 23.0.1 8- Android SDK Build-tools, revision 23 (Obsolete) (...) 162- Google Play Billing Library, revision 5 163- Google Play Licensing Library, revision 2 164- Android Auto API Simulators, revision 1 165- Google Web Driver, revision 2 166- Intel x86 Emulator Accelerator (HAXM installer), revision 6.0.1 To download specific packages you need to specify the number of the item you want to install from the list in the following command: $ ./tools/android update sdk -u -a -t [NO_OF_ITEM_TO_BE_INSTALLED] Example: if I wanted to install Android SDK build tools revision 23.0.1, I would type in: $ ./tools/android update sdk -u -a -t 7 Manual download As not every package (especially the old ones) is listed when you do android sdk list , you can also download things manually. You can manually open the XML file that is shown when during android sdk list - https://dl.google.com/android/repository/repository-11.xml You can find there links to various types of things to download, e.g: ADK http://dl.google.com/android/ADT-XX.0.0.zip SDK Tools http://dl.google.com/android/repository/tools_rXX-linux.zip http://dl.google.com/android/repository/tools_rXX-windows.zip http://dl.google.com/android/repository/tools_rXX-macosx.zip Platform Tools http://dl.google.com/android/repository/platform-tools_rXX-linux.zip http://dl.google.com/android/repository/platform-tools_rXX-windows.zip http://dl.google.com/android/repository/platform-tools_rXX-macosx.zip Build Tools http://dl.google.com/android/repository/build-tools_rXX-linux.zip http://dl.google.com/android/repository/build-tools_rXX-windows.zip http://dl.google.com/android/repository/build-tools_rXX-macosx.zip Platforms http://dl.google.com/android/repository/android-XX.zip To manually download e.g. version 19.0.1 of build tools $ cd android-sdk-linux/build-tools$ wget http://dl.google.com/android/repository/build-tools_r19.0.1-linux.zip$ unzip build-tools_r19.0.1-linux.zip$ mv android-4.4.2 19.0.1$ rm build-tools_r19.0.1-linux.zip Side note (ubuntu): If you're running debian/ubuntu 64-bit, to run aapt you will need to install additional packages: sudo apt-get install lib32stdc++6sudo apt-get install lib32z1 If you're running CentOs (RedHat), to run aapt you will need to install additional packages: sudo yum install zlib.i686 libstd++.i686 While running aapt , if you get an error with GLIBC 2.14 and you dont wont to upgrade your locale GLIBC. Then u need to download the following packages for sdk (build-tool, platform-tool) : build-tool : http://dl.google.com/android/repository/build-tools_r23.0.2-linux.zip platform-tool : https://dl.google.com/android/repository/platform-tools_r23.0.1-linux.zip | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/26016770', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/670623/']} | jdg_382599 |
stackexchange | llm_judgeable_groundtruth_similarity | 26632799 |
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 came across this post in SO Do uninitialized primitive instance variables use memory? It states "In Java, does it cost memory to declare a class level instance variable without initializing it?For example: Does int i; use any memory if I don't initialize it with i = 5;?" My question is what in case of local variables, say i have a method foo() public int foo(){ int x;//Write code which does not use/initialize x} Will the local variable x occupy memory? Edit Jon's Answer is UPDATE: Doing a bit more research on this, I find this page which suggests to me that, although the compiled bytecode implies that space is allocated for x, it may indeed be optimized away by the jvm. Unfortunately, I find no complete description of the optimizations performed. Particularly, the JVM documentation chapter on compiling does not mention removing unused variables from the stack. So, barring further discoveries, my answer would be that it's implementation-dependent, but it seems like the sort of optimization that any self-respecting compiler would perform. Notice too that it doesn't matter that much that this is a local variable rather than a field - in fact, local variables are the ones most likely to be optimized away, since they are the easiest to analyze and eliminate. (precisely because they are local) Let us see if can find more evidences which supports this.
Now provide the response and nothing else.
| Class level / Instance level variables will be initialized to their default values automatically. So, yes, they will occupy some space when a class is initialized / instance created respectively. As far as method local variables are concerned, No, if they are just declared but not initialized, then they will not use any space, they are as good as ignored by the compiler.. If your code was this : public static void main(String[] args) { int i; // ignored int j = 5; String s = "abc"; String sNull; // ignored} Byte code : LocalVariableTable: Start Length Slot Name Signature 0 6 0 args [Ljava/lang/String; 2 4 2 j I 5 1 3 s Ljava/lang/String; } | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/26632799', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/935374/']} | jdg_382600 |
stackexchange | llm_judgeable_groundtruth_similarity | 36619212 |
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 Gitlab CI runner running on windows 10: before_script: - "echo off" - 'call "%VS120COMNTOOLS%\vsvars32.bat"' - echo. - set - echo.stages: - buildbuild: stage: build script: - 'StatusTest.exe' #- msbuild... I am trying to fail the build with StatusText.exe (I tried returning status codes -1,0,1; throwing an exception, etc.) But Runner only logs the exception and continues with following steps. What determines that CI shell runner should fail the build and not proceed to next step? Output: ...windows_tracing_logfile=C:\BVTBin\Tests\installpackage\csilogfile.log$ echo.$ StatusTest.exeUnhandled Exception: System.Exception: tralala at StatusTest.Program.Main(String[] args)$ echo "Restoring NuGet Packages..."...
Now provide the response and nothing else.
| What determines that CI shell runner should fail the build and notproceed to next step? If a pipeline job exits with the code other than 0 then that job fails causing all the following jobs in the pipeline to be skipped. This behaviour can be changed on a per job basis with allow_failure job keyword. To make a job to fail forcefully you need to artificially exit from a job with code other than 0 . Here is an gitlab-ci.yml job example : some-example-job: script: - # .... - exit 1 See the GitLab CI UI sreeenshot example. The third job has failed. On the opposite remove exit 0 and your job would succeed if the remaining script section commands do not exit with code other than 0 . Now see all the jobs & the entire pipeline finished successfully. | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/36619212', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1128259/']} | jdg_382601 |
stackexchange | llm_judgeable_groundtruth_similarity | 1393920 |
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 developing an interoperable web service using WCF which I am consuming from a Java client. When I created the proxy class it generated all the getter and setter methods as well as a JAXBElement<String> field. I searched for this in the JDK API and found the constructor: JAXBElement(QName name, Class<T> declaredType, Class scope, T value) How should I use this constructor? Please explain the parameters and let me know if there is a good tutorial on the Internet describing its use.
Now provide the response and nothing else.
| A solution this problem is, you do not need to create a seperate constructor for creating a JAXBElement . The respected element can be retrieved from objectFactory.create........() method. Suppose you want to create and set some value in response object, and argument is as of JAXBElement type, then you need to do this way: someResponseObj.setMyValue(objectFactory.create.......()); /*method name that will be return a JAXBElement in setter()*/ Note: Please check the ObjectFactory reference because there can be multiple ObjectFactory classes in generated code so you need to refer the exact one which is associated to the class of that package. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/1393920', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/157881/']} | jdg_382602 |
stackexchange | llm_judgeable_groundtruth_similarity | 5105233 |
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 hierarchy: abstract class TicketBase{ public DateTime PublishedDate { get; set; }}class TicketTypeA:TicketBase{ public string PropertyA { get; set; }} class TicketTypeB:TicketBase{ public string PropertyB { get; set; }} In my VM I have a List<TicketBase> Tickets . When a user clicks a button on my app, they want to see a list of previous values of a certain property, e.g.: <Button Tag="{x:Type Types:TicketTypeA}" Command="{Binding ListHistoryCommand}" CommandParameter="{Binding Tag, RelativeSource={RelativeSource Self}}" /> as you can see, I set my Tag property to TicketTypeA and pass that as parameter to my command: private void ListHistory(object o){ if (Tickets.Count == 0) return; Type ty = o as Type; ValueHistory = new ObservableCollection<TicketBase>(GetTicketsOfType(ty).Select(t => t)); // <- Need to return t.PropertyA here, but dynamically}IEnumerable<TicketBase> GetTicketsOfType(Type type){ if (!typeof(TicketBase).IsAssignableFrom(type)) throw new ArgumentException("Parameter 'type' is not a TicketBase"); return Tickets.Where(p => p.GetType() == type);} ( ValueHistory is another collection that I set as ItemsSource on my grid) However I need to also pass in the property name too, so that I can display just that property in the grid like so: Published Time | PropertyA===================================================09:00 | <value of PropertyA at 09:00>08:55 | <value of PropertyA at 08:55> So the question is basically what is the cleanest way to pass in the property name as another parameter into my command?
Now provide the response and nothing else.
| See this question Passing two command parameters using a WPF binding Update If you need to store both the Type and the Property Name on the Button you'll have to use an attached property like you said. To pass the two parameters to the Command, something like this should work <Button Tag="{x:Type Types:TicketTypeA}" local:ParameterNameBehavior.ParameterName="{Binding Source='Parameter A'}" Command="{Binding ListHistoryCommand}"> <Button.CommandParameter> <MultiBinding Converter="{StaticResource PassThroughConverter}"> <Binding Path="Tag" RelativeSource="{RelativeSource Self}"/> <Binding Path="(local:ParameterNameBehavior.ParameterName)" RelativeSource="{RelativeSource Self}"/> </MultiBinding> </Button.CommandParameter></Button> ParameterNameBehavior public static class ParameterNameBehavior{ private static readonly DependencyProperty ParameterNameProperty = DependencyProperty.RegisterAttached("ParameterName", typeof(string), typeof(ParameterNameBehavior)); public static void SetParameterName(DependencyObject element, string value) { element.SetValue(ParameterNameProperty, value); } public static string GetParameterName(DependencyObject element) { return (string)element.GetValue(ParameterNameProperty); }} PassThroughConverter public class PassThroughConverter : IMultiValueConverter{ public object Convert(object[] values, Type targetType, object parameter, CultureInfo culture) { return values.ToList(); } public object[] ConvertBack(object value, Type[] targetTypes, object parameter, CultureInfo culture) { throw new NotSupportedException(); }} | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/5105233', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/229581/']} | jdg_382603 |
stackexchange | llm_judgeable_groundtruth_similarity | 49961149 |
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 archive pdf files from remote websites to Google Cloud Storage using a google function triggered by a firebase write. The code below works. However, this function copies the remote file to the bucket root. I'd like to copy the pdf to the pth of the bucket: library-xxxx.appspot.com/Orgs/${params.ukey} . How to do this? exports.copyFiles = functions.database.ref('Orgs/{orgkey}/resources/{restypekey}/{ukey}/linkDesc/en').onWrite(event => { const snapshot = event.data; const params = event.params; const filetocopy = snapshot.val(); if (validFileType(filetocopy)) { const pth = 'Orgs/' + params.orgkey; const bucket = gcs.bucket('library-xxxx.appspot.com') return bucket.upload(filetocopy) .then(res => { console.log('res',res); }).catch(err => { console.log('err', err); }); }});
Now provide the response and nothing else.
| Let me begin with a brief explanation of how GCS file system works: as explained in the documentation of Google Cloud Storage , GCS is a flat name space where the concept of directories does not exist. If you have an object like gs://my-bucket/folder/file.txt , this means that there is an object called folder/file.txt stored in the root directory of gs://my-bucket , i.e. the object name includes / characters. It is true that the GCS UI in the Console and the gsutil CLI tool make the illusion of having a hierarchical file structure, but this is only to provide more clarity for the user, even though those directories do not exist, and everything is stored in a "flat" name space. That being said, as described in the reference for the storage.bucket.upload() method , you can specify an options parameter containing the destination field, where you can specify a string with the complete filename to use. Just as an example (note the options paramter difference between both functions): var bucket = storage.bucket('my-sample-bucket');var options = { destination: 'somewhere/here.txt'};bucket.upload('sample.txt', function(err, file) { console.log("Created object gs://my-sample-bucket/sample.txt");});bucket.upload('sample.txt', options, function(err, file) { console.log("Created object gs://my-sample-bucket/somewhere/here.txt");}); So in your case you can build a string containing the complete name that you want to use (containing also the "directory" structure you have in mind). | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/49961149', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/5154097/']} | jdg_382604 |
stackexchange | llm_judgeable_groundtruth_similarity | 277997 |
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:
Calculate inertia tensors This topic inspired me to experiment with calculating tensors of more complex shapes of rigid bodies (I did not find them in the Mathematica database). For simple shapes of rigid bodies, everything works great: MomentOfInertia[Ball[{0, 0, 0}, R]];MomentOfInertia[Cone[{{0, 0, 0}, {0, a, 0}}, R]];MomentOfInertia[Cylinder[{{0, -1/2, 0}, {0, 1/2, 0}}, R]]; Remark: https://mathematica.stackexchange.com/a/62895/67019 The code from here also works and gives similar results. My question: And how to calculate the inertia tensor for more complex rigid bodies. For example, for a sector of a torus or a ring with a rectangular cross section? This picture from SolidWorks.
Now provide the response and nothing else.
| Here is an example for half a torus. r0 = 1; (*center radius*)r1 = 0.2;(*outer radius*)Region[ParametricRegion[{(r0 + r*Cos[θ]) Cos[ϕ], (r0 + r*Cos[θ]) Sin[ϕ], r*Sin[θ]}, {{r, 0, r1}, {θ, 0, 2 π}, {ϕ, 0, π}}], Axes -> True] The mass density is assumed to be 1. For other values you simply multiply the result by this value. The inertia tensor relative to the coordinate axes is then: reg = ParametricRegion[{(r0 + r*Cos[θ]) Cos[ϕ], (r0 + r*Cos[θ]) Sin[ϕ], r*Sin[θ]}, {{r, 0, r1}, {θ, 0, 2 π}, {ϕ,0, π}}];tensor = Outer[Times, {x, y, z}, {x, y, z}]NIntegrate[tensor, {x, y, z} ∈ reg](* {{x^2, x y, x z}, {x y, y^2, y z}, {x z, y z, z^2}} *)(* {{0.20109, 0.00010941, 2.40669*10^-6}, {0.0000312697, 0.200579, 0.0000373482}, {-0.0000400759, -9.15108*10^-7, 0.00384308}} *) Addendum The cross section is given by the terms: r*Cos[θ] and r*Sin[θ] . To change the cross section we simply need to change these terms. E.g. a quadratic cross section: r0 = 1; w = 0.2;Region[ParametricRegion[{(r0 + x1) Cos[ϕ], (r0 + x1) Sin[ϕ], y1}, {{x1, -w, w}, {y1, -w, w}, {ϕ, 0, π}}], Axes -> True] | {} | {'log_upvote_score': 4, 'links': ['https://mathematica.stackexchange.com/questions/277997', 'https://mathematica.stackexchange.com', 'https://mathematica.stackexchange.com/users/67019/']} | jdg_382605 |
stackexchange | llm_judgeable_groundtruth_similarity | 14853939 |
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 Jersey in my Web-application. The data sent to the server is in JSON format, which in turn is unmarshalled at the server-end and the object obtained is used in further processing. The security audit raised some vulnerabilities for this approach. My Rest Code: @POST@Path("/registerManga")@Produces(MediaType.APPLICATION_JSON)public Response registerManga(MangaBean mBean){ System.out.println(mBean); return Response.status(200).build();} MangaBean: public class MangaBean { public String title; public String author; @Override public String toString() { return "MangaBean [title=" + title + ", author=" + author + "]"; } public String getTitle() { return title; } public void setTitle(String title) { this.title = title; } public String getAuthor() { return author; } public void setAuthor(String author) { this.author = author; }} The data is sent in this format: ["title":"Bleach","author":"kubo tite"] The above data is successfully unmarshalled into an object and I get this as the output: MangaBean [title=Bleach, author=kubo tite] But if the data is changed to: ["title":"<script>alert("123");</script>","author":"kubo tite"] A 500 internal server error occurs and is displayed to the user: javax.servlet.ServletException: org.codehaus.jackson.JsonParseException: Unexpected character ('1' (code 49)): was expecting comma to separate OBJECT entries at [Source: org.apache.catalina.connector.CoyoteInputStream@19bd1ca; line: 1, column: 28] com.sun.jersey.spi.container.servlet.WebComponent.service(WebComponent.java:420) com.sun.jersey.spi.container.servlet.ServletContainer.service(ServletContainer.java:537) com.sun.jersey.spi.container.servlet.ServletContainer.service(ServletContainer.java:699) javax.servlet.http.HttpServlet.service(HttpServlet.java:717) The unexpected occurrence of "" is causing errors in the parser. As the unmarshalling is done behind the scenes and I have no control over it, I am unable to handle the exception being raised. My question is how can I handle this exception and return a proper response to the user instead of a stacktrace. Please advice.
Now provide the response and nothing else.
| Register an exception mapper to handle the JSON parsing exceptions: @Providerclass JSONParseExceptionMapper implements ExceptionMapper< JsonParseException > { @Override public Response toResponse(final JsonParseException jpe) { // Create and return an appropriate response here return Response.status(Status.BAD_REQUEST) .entity("Invalid data supplied for request").build(); }} | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/14853939', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1580892/']} | jdg_382606 |
stackexchange | llm_judgeable_groundtruth_similarity | 15558 |
Below is a question asked on the forum bioinformatics.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a collection of biological parts and devices in a particular format that basically stores information of the sequence of the elements. My intention is to move to a more standardized data structure with a particular interest in Synthetic Biology. SBOL 3 looks like a good choice, then the question is if there is a way to kind of "import" data from my sequence-based database into SBOL?
Now provide the response and nothing else.
| For SBOL 2, you can readily import data via the online converter tool at https://converter.sbolstandard.org/ The converter basically just wraps the conversion function found in the SBOL libraries, so if you're coding, you can do the conversion directly from the libraries. For SBOL 3, there isn't yet an online tool, but James McLaughlin has a converter in his JavaScript library: https://github.com/sboltools/sbolgraph I believe he is working to bring it online shortly, so hopefully this answer will soon need to be updated or replaced by an answer from him. An anecdote on the difficulty level: I recently started using an SBOL3-->SBOL2-->GenBank conversion using pySBOL3 and pySBOL3. It took a couple of hours to setup the pipeline, and isn't perfect, but it's pretty doable (and ought to be generalized for others to use as well at some point). The other way would be easier, since GenBank contents are pretty simple. | {} | {'log_upvote_score': 4, 'links': ['https://bioinformatics.stackexchange.com/questions/15558', 'https://bioinformatics.stackexchange.com', 'https://bioinformatics.stackexchange.com/users/10755/']} | jdg_382607 |
stackexchange | llm_judgeable_groundtruth_similarity | 39139393 |
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 [mapping] with 2 columns similar to below id | values1 | 1,22 | 1,2,33 | 1,14 | 1,1,2 and another table [map] is similar to this sno | values1 | Test2 | Hello3 | Hai My expected output is id | values1 | Test,Hello2 | Test,Hello,Hai3 | Test,Test4 | Test,Test,Hello Is it possible? If it is please can anybody build a query for me.
Now provide the response and nothing else.
| You can use MySQL FIND_IN_SET() to join the tables and GROUP_CONCAT() to concat the values : SELECT s.sno,GROUP_CONCAT(s.values) as `values` FROM mapping tINNER JOIN map s ON(FIND_IN_SET(s.id,t.values))GROUP BY s.sno Note: You should know that this is a very bad DB structure. This may lead to a lot more complicated queries and will force you to over complicate things. You should Normalize your data, split it , and place each ID in a separate record! | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/39139393', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3568000/']} | jdg_382608 |
stackexchange | llm_judgeable_groundtruth_similarity | 4906073 |
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 decided to save setting in xml file since field takes only one value. My XML file is like <?xml version="1.0" encoding="UTF-8"?><setting> <setting1>setting1 value</setting1> <setting2>setting2 value</setting2> <setting3>setting3 value</setting3> .... .... ....</setting> Can anyone suggest me a simple php script to read, edit, add, and delete node and node values?
Now provide the response and nothing else.
| If your XML is really that simple, you can use SimpleXML to CRUD it. SimpleXml will parse the XML into a tree structure of SimpleXmlElements. In a nutshell, you use it like this: // CREATE$config = new SimpleXmlElement('<settings/>');$config->setting1 = 'setting1 value'; $config->saveXML('config.xml'); // READ$config = new SimpleXmlElement('config.xml');echo $config->setting1;echo $config->asXml();// UPDATE$config->setting1 = 'new value';$config->setting2 = 'setting2 value';echo $config->asXml();// DELETEunset($config->setting1);$config->setting2 = NULL;echo $config->asXML();unlink('config.xml'); Please refer to the PHP manual for further usage examples and the API description . On a sidenote, if you really just have key/value pairs, you could also use a plain old PHP array to store them or a key/value store like DBA or even APC and memcached with a long ttl. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/4906073', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/447023/']} | jdg_382609 |
stackexchange | llm_judgeable_groundtruth_similarity | 33685735 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm trying to create a route in Laravel 5.1 that will search the records base on "keyword". I like to include a ? in my url for more readability. The problem is that when I'm including the ? and test the route with postman it returns nothing. But when I remove the ? and replaced it with / and test it with postman again it will return the value of keyword. Does Laravel route supports ? ? //Routes.phpRoute::get('/search?keyword={keyword}', [ 'as' => 'getAllSearchPublications', 'uses' => 'PublicationController@index']);//Publication Controllerpublic function index($keyword){ return $keyword;} I've been searching the internet for hours now and I've read the Laravel documentation, But I can't find the answer. Thank you.
Now provide the response and nothing else.
| I believe you are talking about query strings. To accept query parameters, you don't pass it as an argument. So, for example, your route should look more plain like this: Route::get('/search', [ 'as' => 'getAllSearchPublications', 'uses' => 'PublicationController@index']); Note: I dropped ?keyword={keyword} . Then, in your controller method, you can grab the query parameter by calling the query method on your Request object. public function index(Request $request){ return $request->query('keyword');} If you didn't already, you will need to import use Illuminate\Http\Request; to use the Request class. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/33685735', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3736192/']} | jdg_382610 |
stackexchange | llm_judgeable_groundtruth_similarity | 49525141 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
The Kafka controller in a Kafka cluster is in charge of managing partition leaders and replication. If there are 100 brokers in a Kafka cluster, is the controller just one Kafka broker? So out of the 100 brokers, is the controller the leader? How would you know which broker is the controller? Is the management of the Kafka Controller critical to Kafka system management?
Now provide the response and nothing else.
| Within a Kafka cluster, a single broker serves as the active controller which is responsible for state management of partitions and replicas. So in your case, if you have a cluster with 100 brokers, one of them will act as the controller. More details regarding the responsibilities of a cluster controller can be found here . In order to find which broker is the controller of a cluster you first need to connect to Zookeeper through ZK CLI: ./bin/zkCli.sh -server localhost:2181 and then get the controller [zk: localhost:2181(CONNECTED) 0] get /controller The output should look like the one below: {"version":1,"brokerid":100,"timestamp":"1506423376977"}cZxid = 0x191ctime = Tue Sep 26 12:56:16 CEST 2017mZxid = 0x191mtime = Tue Sep 26 12:56:16 CEST 2017pZxid = 0x191cversion = 0dataVersion = 0aclVersion = 0ephemeralOwner = 0x15ebdd241840002dataLength = 56numChildren = 0 Zookeeper is the storage of the state of a Kafka cluster. It is used for the controller election either in the very beginning or when the current controller crashes. The controller is also responsible for telling other replicas to become partition leaders when the partition leader broker of a topic fails/crashes. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/49525141', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/9538647/']} | jdg_382611 |
stackexchange | llm_judgeable_groundtruth_similarity | 57120255 |
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 trying to create a Kafka Consumer for a topic without using the @KafkaListener annotation. I want to do this because I am trying to dynamically create listeners based on the application.properties without the use of spring boot. I figured the best route for this would be to manually create a KafkaListenerContainerFactory Could someone please provide an example of how to do this in it's own class.
Now provide the response and nothing else.
| with spring @Beanpublic KafkaMessageListenerContainer<String, String> messageListenerContainer(String topic) { ContainerProperties containerProperties = new ContainerProperties(topic); containerProperties.setMessageListener(new MyMessageListener()); ConsumerFactory<String, String> consumerFactory = new DefaultKafkaConsumerFactory<>(consumerProperties()); KafkaMessageListenerContainer<String, String> listenerContainer = new KafkaMessageListenerContainer<>(consumerFactory, containerProperties); listenerContainer.setAutoStartup(false); // bean name is the prefix of kafka consumer thread name listenerContainer.setBeanName("kafka-message-listener"); return listenerContainer;}private Map<String, Object> consumerProperties(){ Map<String, Object> props = new HashMap<>(); props.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, "localhost:9092"); props.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class); props.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class); props.put(ConsumerConfig.GROUP_ID_CONFIG, "test"); return props;}static class MyMessageListener implements MessageListener<String, String> @Override public void onMessage(ConsumerRecord<String, String> data) { // do something }} without spring kafka documentation is very helpful. below is a usage example from it. Properties props = new Properties(); props.setProperty("bootstrap.servers", "localhost:9092"); props.setProperty("group.id", "test"); props.setProperty("enable.auto.commit", "true"); props.setProperty("auto.commit.interval.ms", "1000"); props.setProperty("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer"); props.setProperty("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer"); KafkaConsumer<String, String> consumer = new KafkaConsumer<>(props); consumer.subscribe(Arrays.asList("foo", "bar")); while (true) { ConsumerRecords<String, String> records = consumer.poll(Duration.ofMillis(100)); for (ConsumerRecord<String, String> record : records) System.out.printf("offset = %d, key = %s, value = %s%n", record.offset(), record.key(), record.value()); } | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/57120255', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/11794142/']} | jdg_382612 |
stackexchange | llm_judgeable_groundtruth_similarity | 45160 |
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 Über die Bestimmung asymptotischer Gesetze in der Zahlentheorie , Dirichlet proved his theorem on the asymptoticbehaviour of the divisor function using a Lambert series: let $d_n = d(n)$ denote the number of the divisors of $n$; then Lambert (actually this is due to Euler) observed that$$ f(z) = \sum_{n=1}^\infty d_n z^n = \sum_{n=1}^\infty \frac{z^n}{1-z^n} . $$This series converges for $|z| < 1$, and diverges for $z = 1$. Setting $z = e^{-t}$ we obtain$$ g(t) = \sum_{n=1}^\infty \frac{e^{-nt}}{1-e^{-nt}} = \sum_{n=1}^\infty \frac{1}{e^{nt}-1} . $$ Dirichlet writes that "expressing this series by a definite integralone easily finds" that $$ g(t) \sim \frac1t \log \frac1t + \frac{\gamma}t $$as $t \to 0$, where $\gamma$ is Euler's constant. Dirichlet then claims that the asymptotic behaviour of $g(t)$would imply that $d_n$ is, on the average, equal to $\log n + 2 \gamma$,which in turn implies that $b_1 + b_2 + \ldots + b_n \approx (n + \frac12) \log n + (2\gamma+1)n. $He mentions that he has used the integral expressions for $\Gamma(k)$and its derivative $\Gamma'(k)$ for deriving the first property. Knopp (Über Lambertsche Reihen, J. Reine Angew. Math. 142) claims that Dirichlet's proof was "heuristic". I find that hard to believe, and I am convinced that Dirichlet's sketch can be turned into a valid proof by someone who knows the tools of the trade. So here are my questions: How did Dirichlet express "this series by a definite integral" and derive the asymptotic expression for $g(t)$? Let me remark that Endres and Steiner ( A new proof of the Voronoi summation formula ) use Voronoi summation for proving the sharper estimate$$ g(t) \sim \frac1t \log \frac1t + \frac{\gamma}t + \frac14 + O(t) $$as $t \to 0$. But this is not "easily found". How did Dirichlet transform his knowledge about the asymptoticbehaviour of $\sum b_n e^{-nt}$ as $t \to 0$ into an averagebehaviour of $b_n$? This smells like a Tauberian result, but I'm notfluent enough in analytic number theory to see how easy this is.
Now provide the response and nothing else.
| For part 1 of the question, he would most likely have used the Euler-Maclaurin summation formula $$\sum_{n=1}^{\infty}\frac{1}{e^{nt} - 1} = \int_{1}^{\infty}\frac{dx}{e^{xt} - 1} + \frac{1}{2}\frac{1}{e^t - 1} + \int_{1}^{\infty}S(x)\left(\frac{d}{dx}\frac{1}{e^{xt} - 1}\right)dx$$ with $S(x)$ the sawtooth function. It is easy to obtain the leading term, because it comes from the first integral $$\int_{1}^{\infty}\frac{dx}{e^{xt} - 1} = \frac{1}{t}\int_{t}^{\infty}\frac{du}{e^u - 1}$$ by the change of variable $u = xt$. We have $$\int_{t}^{\infty}\frac{du}{e^u - 1} = \int_{t}^{1}\frac{du}{e^u - 1} + \int_{1}^{\infty}\frac{du}{e^u - 1},$$and $$\frac{1}{e^u - 1} = \frac{1}{u} + \left(\frac{1}{e^u - 1} - \frac{1}{u}\right)$$on $0 \leq u \leq 1$, so that $$g(t) = \frac{1}{t}\log\left(\frac{1}{t}\right) + O\left(\frac{1}{t}\right).$$But to get the second term looks harder, for the integral with the sawtooth function contributes to that term. To go further, one can integrate by parts in that integral, which is the standard approach, or write it as a sum of integrals over the intervals from $n$ to $n+1$. Also the sawtooth function has a simple Fourier expansion, which may help. I should remark that the integral with the sawtooth function is $O(1/t)$ as one sees when bounding it by passing the absolute value under the integral sign and using $|S(x)| \leq 1/2$. Anyway, I am pretty sure that part 1 is doable with some work. Part 2 looks trickier. The Lambert series expansion $$\sum_{n=1}^{\infty}(1 + \mu(n))e^{-nt} = \frac{e^{-t}}{1 - e^{-t}} + e^{-t} = \frac{1}{t} + \frac{1}{2} + O(|t|)$$ is a little nicer than the one for the divisor function; not only are the coefficients nonnegative, but they are also bounded. Supposing that we have a Tauberian theorem strong enough to yield $$\sum_{n \leq x}(1 + \mu(n)) \sim x,$$ we would then have proved the Prime Number Theorem from the Lambert series. It seems a little unlikely that Dirichlet had such a strong Tauberian theorem; would he not have proved the Prime Number Theorem if he had? Of course, this argument by analogy is not conclusive, since the two situations differ by a factor of $\log(x)$. We shall never know what argument Dirichlet had, and he may have found an approach that did not use a Tauberian theorem, perhaps exploiting special properties of the divisor function. It is worth noting that Voronoi's first proof of the error term $O(x^{1/3}\log(x))$ for the divisor problem was based on the Euler-Maclaurin summation formula. | {} | {'log_upvote_score': 5, 'links': ['https://mathoverflow.net/questions/45160', 'https://mathoverflow.net', 'https://mathoverflow.net/users/3503/']} | jdg_382613 |
stackexchange | llm_judgeable_groundtruth_similarity | 32971 |
Below is a question asked on the forum mechanics.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
My car battery drained itself after a week of not being used. I was researching how to identify the cause, and saw a comment under this article saying: What if I am not detecting a reading but the battery still drains? You could have a fuse that is draining your battery. [Not Helpful 5 ] [Helpful 7 ] This sounds like my situation - there's not much drain, but I've had heaps of problems with the fuses (a previous owner "fixed" blown fuses by wrapping copper wire around them, which in one case fell apart inside the fuse box... ugh!) But I don't understand how a fuse could cause drain like this, or, if I can't measure such drain the normal way, how I could identify that this is the problem and how I could fix it. Can someone elaborate? What you do if you had a car (97 Toyota RAV4) with no draining electrics, a relatively new battery (six months), high temperature all year, seemed to have a normal level of amp draw when off, but a historically dodgy fusebox and a self-draining battery?
Now provide the response and nothing else.
| It wouldn't be the fuse which is causing the power drain, but the circuit the fuse is there to protect. (This is the reason why the copied area you have posted has 5 "Not Helpful" votes against it.) The fuse is only a conduit. It transmits electricity. When the circuit transmits too much electricity, the fuse heats up, then "pops", not allowing anymore electricity to flow. The fuse in and of itself cannot be the cause of the power drain. It is, however, an indication of where the power drain is coming from. If by pulling the fuse you get a noticeable drop in battery drain, whatever is causing the drain is on that circuit. It will help you narrow down what exactly is going on. While batteries do lose power over the long term by just sitting, it should only lose about 5% of its reserve per month ... which in the grand scheme of things isn't a lot. Find the circuit which has the power drain on it, then find what's on that circuit to kill the aggressor. This post may be of further assistance to you. | {} | {'log_upvote_score': 4, 'links': ['https://mechanics.stackexchange.com/questions/32971', 'https://mechanics.stackexchange.com', 'https://mechanics.stackexchange.com/users/13299/']} | jdg_382614 |
stackexchange | llm_judgeable_groundtruth_similarity | 42036810 |
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 protect ASP.NET Core Web API using JWT. Additionally, I would like to have an option of using roles from tokens payload directly in controller actions attributes. Now, while I did find it out how to use it with Policies: Authorize(Policy="CheckIfUserIsOfRoleX")ControllerAction()... I would like better to have an option to use something usual like: Authorize(Role="RoleX") where Role would be automatically mapped from JWT payload. { name: "somename", roles: ["RoleX", "RoleY", "RoleZ"]} So, what is the easiest way to accomplish this in ASP.NET Core? Is there a way to get this working automatically through some settings/mappings (if so, where to set it?) or should I, after token is validated, intercept generation of ClaimsIdentity and add roles claims manually (if so, where/how to do that?)?
Now provide the response and nothing else.
| You need get valid claims when generating JWT. Here is example code: Login logic: [HttpPost][AllowAnonymous]public async Task<IActionResult> Login([FromBody] ApplicationUser applicationUser) { var result = await _signInManager.PasswordSignInAsync(applicationUser.UserName, applicationUser.Password, true, false); if(result.Succeeded) { var user = await _userManager.FindByNameAsync(applicationUser.UserName); // Get valid claims and pass them into JWT var claims = await GetValidClaims(user); // Create the JWT security token and encode it. var jwt = new JwtSecurityToken( issuer: _jwtOptions.Issuer, audience: _jwtOptions.Audience, claims: claims, notBefore: _jwtOptions.NotBefore, expires: _jwtOptions.Expiration, signingCredentials: _jwtOptions.SigningCredentials); //... } else { throw new ApiException('Wrong username or password', 403); }} Get user claims based UserRoles , RoleClaims and UserClaims tables (ASP.NET Identity): private async Task<List<Claim>> GetValidClaims(ApplicationUser user){ IdentityOptions _options = new IdentityOptions(); var claims = new List<Claim> { new Claim(JwtRegisteredClaimNames.Sub, user.UserName), new Claim(JwtRegisteredClaimNames.Jti, await _jwtOptions.JtiGenerator()), new Claim(JwtRegisteredClaimNames.Iat, ToUnixEpochDate(_jwtOptions.IssuedAt).ToString(), ClaimValueTypes.Integer64), new Claim(_options.ClaimsIdentity.UserIdClaimType, user.Id.ToString()), new Claim(_options.ClaimsIdentity.UserNameClaimType, user.UserName) }; var userClaims = await _userManager.GetClaimsAsync(user); var userRoles = await _userManager.GetRolesAsync(user); claims.AddRange(userClaims); foreach (var userRole in userRoles) { claims.Add(new Claim(ClaimTypes.Role, userRole)); var role = await _roleManager.FindByNameAsync(userRole); if(role != null) { var roleClaims = await _roleManager.GetClaimsAsync(role); foreach(Claim roleClaim in roleClaims) { claims.Add(roleClaim); } } } return claims;} In Startup.cs please add needed policies into authorization: void ConfigureServices(IServiceCollection service) { services.AddAuthorization(options => { // Here I stored necessary permissions/roles in a constant foreach (var prop in typeof(ClaimPermission).GetFields(BindingFlags.Public | BindingFlags.Static | BindingFlags.FlattenHierarchy)) { options.AddPolicy(prop.GetValue(null).ToString(), policy => policy.RequireClaim(ClaimType.Permission, prop.GetValue(null).ToString())); } });} ClaimPermission: public static class ClaimPermission{ public const string CanAddNewService = "Tự thêm dịch vụ", CanCancelCustomerServices = "Hủy dịch vụ khách gọi", CanPrintReceiptAgain = "In lại hóa đơn", CanImportGoods = "Quản lý tồn kho", CanManageComputers = "Quản lý máy tính", CanManageCoffees = "Quản lý bàn cà phê", CanManageBillards = "Quản lý bàn billard";} Use the similar snippet to get all pre-defined permissions and insert it to asp.net permission claims table: var staffRole = await roleManager.CreateRoleIfNotExists(UserType.Staff);foreach (var prop in typeof(ClaimPermission).GetFields(BindingFlags.Public | BindingFlags.Static | BindingFlags.FlattenHierarchy)){ await roleManager.AddClaimIfNotExists(staffRole, prop.GetValue(null).ToString());} I am a beginner in ASP.NET, so please let me know if you have better solutions. And, I don't know how worst when I put all claims/permissions into JWT. Too long? Performance ? Should I store generated JWT in database and check it later for getting valid user's roles/claims? | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/42036810', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2736919/']} | jdg_382615 |
stackexchange | llm_judgeable_groundtruth_similarity | 6878662 |
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 able to upload one picture but I can't create a photoset with multiple images using API. Documentation says:Paramater: Array (URL-encoded binary contents) One or more image files (submit multiple times to create a slide show) Does anyone know how to do it?
Now provide the response and nothing else.
| It's kind of a painful process, but I figured it out after studying the python code Tumblr posted . In short, it requires getting the hexadecimal for the photo and then doing some substitutions. I've created a simple iOS / iPad / iPhone project on GitHub that uploads multiple photos to photosets using the Tumblr API , based heavily on the ASIHTTPRequest+OAuth project . It works so far in my limited testing -- feel free to make use of it and let me know how it goes. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/6878662', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/826387/']} | jdg_382616 |
stackexchange | llm_judgeable_groundtruth_similarity | 10428158 |
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 logging messages using Enterprise Library. I want some of these (typically errors and warnings) to be passed to the Windows event-system). I today route these via entlib.config. This solution works and so far, so good. But, I have more needs than what this solution provides me. I have multiple installations that should log to different logs, but I want their names to be logical and intuitive in the event-viewer. But, the Windows event-system cannot have two categories where the first 8 characters in the name are the same. The category-name can be longer, but only the first 8 letters is used to distinguish them. .Net actually outputs a warning if this happens: Only the first eight characters of a custom log name are significant, and there is already another log on the system using the first eight characters of the name given. Currently I have to resort to cryptical prefixes, but I am still in danger of having multiple installations "colliding" with each other in regrads to the logname, so I need a better solution. However, in the event viewer on my computer I can see that there are also hierarchies of lognames - which is exactly what I need. Both Microsoft and Cisco obviously has found a way to do this: But, how can I create such an hierarchy for logging, where each application may be installed a number of times? Like this: CompanyName ApplicationName Installation1 Installation2
Now provide the response and nothing else.
| .NET 4 Answer What it looks like you are seeing are the channels from Event Tracing for Windows (ETW). You can see the relevant items in the registry at HKLM\SOFTWARE\Microsoft\Windows\CurrentVersion\WINEVT . To use those features you would have to use the new Windows Event Log functionality which supersedes the Event Logging API starting from Vista and looks like it is mainly targeted at C/C++ development. It does appear that some of this is exposed via the System.Diagnostics.Eventing Namespace . I found a good overview of ETW to be Improve Debugging And Performance Tuning With ETW . The good news is that it looks like you can do what you want. You will need to create an XML manifest that contains provider information as well as the events that will be logged. Then you need to use the Message Compiler (MC.EXE!) on the manifest to create header, resource files, and logging classes and then register the provider. If you download Microsoft Windows SDK for Windows 7 and .NET Framework 4 you will find in the Samples\winbase\Eventing\Provider\Simple\CSharp subdirectory a .NET sample solution that should lead you through all the steps. While it does meet your hierarchical requirement and is sort of cool, for a typical line of business application this might be a bit of overkill in terms of complexity. Also, the code generated by the message compiler is unsafe code so that may also be a negative. .NET 4.5 Answer In .NET 4.5 there is much better support for ETW using the EventSource class. See Windows high speed logging: ETW in C#/.NET using System.Diagnostics.Tracing.EventSource for an introduction. There is also now Event Log support with EventSource. See Announcing the EventSource NuGet Package – Write to the Windows Event Log for a walkthrough. Basically, at compile time a manifest and manifest DLL are generated for each EventSource and these can be registered using wevtutil.exe. With the addition of EventSource and Event Log channel support this approach now looks to be straight forward and viable. Finally, note for those interested in ETW that the patterns & practices team has an application block Semantic Logging Application Block that can use ETW. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/10428158', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/95008/']} | jdg_382617 |
stackexchange | llm_judgeable_groundtruth_similarity | 14260701 |
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 wrote an app for Windows Phone 7, recently I've upgraded it to Windows Phone 8 and I plan on adding some features. Unfortunately, I've run into a problem immediately after the upgrade. The main part of the app is a Panorama control that is databound. On SelectionChanged I am fetching the data for the new PanoramaItem + 1 (preselecting data so it's there when the person eventually goes to the item). That worked fine in WP7 but the SelectionChanged event doesn't fire with WP8. I've reproduced the issue with a new WP8 app that wasn't upgraded and it's also isolated to databound controls. If I statically add PanoramaItems the SelectionChanged event fires fine. Am I missing something or is this just a straight up bug in WP8? Any recommended work-arounds? I have a GitHub repo with a static sample and a databound sample to show what works and what doesn't work. https://github.com/bthubbard/DatabindingIssues
Now provide the response and nothing else.
| The Panorama control in WP8 has a known databinding bug. The symptoms of the bug are that SelectionChanged doesn't fire, SelectedIndex & SelectedItem aren't reliable and that back navigation into a page with Panorama resets the panorama selected item. For example, the following code sample will never fire the MessageBox and SelectedIndex & SelectedItem won't indicate the correct expected values. <phone:Panorama x:Name="panorama" ItemsSource="{Binding}" SelectionChanged="Panorama_SelectionChanged_1"> <phone:Panorama.HeaderTemplate> <DataTemplate> <ContentControl Content="{Binding Name}" /> </DataTemplate> </phone:Panorama.HeaderTemplate> <phone:Panorama.ItemTemplate> <DataTemplate> <ContentControl Content="{Binding Name}" /> </DataTemplate> </phone:Panorama.ItemTemplate></phone:Panorama> private void MainPage_Loaded(object sender, RoutedEventArgs e){ this.DataContext = new ObservableCollection<Cow>() { new Cow("Foo"), new Cow("Bar"), new Cow("Baz") };}private void Panorama_SelectionChanged_1(object sender, SelectionChangedEventArgs e){ MessageBox.Show("Panorama_SelectionChanged_1: " + panorama.SelectedIndex);}public class Cow{ public Cow(string name) { Name = name; } public string Name { get; set; }} One obvious fix will be to manually initialize PanoramaItems in code-behind. Another solution would be to change our collection from typed to untyped, and add the following code snippet to our bounded data class. So let's change our code from ObservableCollection<Cow> to ObservableCollection<object> and add some code to the Cow class: private void MainPage_Loaded(object sender, RoutedEventArgs e){ this.DataContext = new ObservableCollection<object>() { new Cow("Foo"), new Cow("Bar"), new Cow("Baz") };}public class Cow{ public Cow(string name) { Name = name; } public string Name { get; set; } public override bool Equals(object obj) { if ((obj != null) && (obj.GetType() == typeof(PanoramaItem))) { var thePanoItem = (PanoramaItem)obj; return base.Equals(thePanoItem.Header); } else { return base.Equals(obj); } } public override int GetHashCode() { return base.GetHashCode(); }} Now, when we run this code snippet we can see SelectionChanged fires as expected with the correct SelectedIndex values: | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/14260701', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/330376/']} | jdg_382618 |
stackexchange | llm_judgeable_groundtruth_similarity | 22533037 |
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 below code. I am using Oracle 11g. SELECT DBMS_OBFUSCATION_TOOLKIT.md5 (input => UTL_RAW.cast_to_raw( FIRST_NAME ||LAST_NAME )) md5_key , FIRST_NAME , LAST_NAMEFROM C_NAME_TABWHERE PKEY='1234' How can i call this code? Can i directly execute this code in sqldeveloper?
Now provide the response and nothing else.
| In Oracle 12c you can use the function STANDARD_HASH . It does not require any additional privileges. select standard_hash('foo', 'MD5') from dual; The dbms_obfuscation_toolkit is deprecated (see Note here ). You can use DBMS_CRYPTO directly: select rawtohex( DBMS_CRYPTO.Hash ( UTL_I18N.STRING_TO_RAW ('foo', 'AL32UTF8'), 2) ) from dual; Output: ACBD18DB4CC2F85CEDEF654FCCC4A4D8 Add a lower function call if needed. More on DBMS_CRYPTO . | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/22533037', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/755806/']} | jdg_382619 |
stackexchange | llm_judgeable_groundtruth_similarity | 21085 |
Below is a question asked on the forum scicomp.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Why do people use the classical least squares approach so often ? If I use the absolute value instead of the power, I immediately know how far away the solution is: $$ res = \frac{abs(x - x_{model})}{x}$$ What is the benefit of squaring ?
Now provide the response and nothing else.
| Why do people use the classical least squares approach so often? Primarily, squaring makes the problem twice-differentiable, thus many different solution methods apply (quasi-Newton methods, Levenberg-Marquardt, Gauss-Newton), and there is still some flexibility with respect to what is being squared (e.g., I can replace $x$ with $f(x)$ for a wide class of functions $f$). From these methods, there are some nice linear algebra benefits, too: we can use Cholesky/sparse Cholesky. If I use the absolute value instead of the power, I immediately know how far away the solution is... The absolute value approach (more generally, L1-minimization approaches) can sometimes be tractable, if an LP reformulation is possible, but it can also really slow things down if an LP formulation is not possible (e.g., taking the L1 norm of a difference of nonlinear functions). | {} | {'log_upvote_score': 5, 'links': ['https://scicomp.stackexchange.com/questions/21085', 'https://scicomp.stackexchange.com', 'https://scicomp.stackexchange.com/users/3957/']} | jdg_382620 |
stackexchange | llm_judgeable_groundtruth_similarity | 8066253 |
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 way to compute a Java class's method's signature? A signature like ([Ljava/lang/String;)V represents a function that takes a String[] as argument and returns void . What's the rule to compute the signature?
Now provide the response and nothing else.
| It's always a set of parentheses enclosing type signifiers for the arguments, one after the other with no commas or anything, followed by a type signifier for the return value after the closing paren. It's pretty straightforward. There's a table of type signatures on this page: Signature Java TypeZ booleanB byteC charS shortI intJ longF floatD doubleV voidL fully-qualified-class ; fully-qualified-class[ type type[] Those last two mean that to name a class, you say, for example, Ljava/lang/Object; , and to name an array of (for example) int , you say [I , and an array of array of int is [[I . If you wanted to literally compute the signature in Java code based on reflection, it'd be simple enough; just use the table above with rules for handling objects and arrays. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/8066253', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/791713/']} | jdg_382621 |
stackexchange | llm_judgeable_groundtruth_similarity | 32184744 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Looking through Hapi's documentation, and trying to google, I can find how to setup a 404 page, but I cannot find anything about setting up a 500 page. I tried adding an error handler like follows: server.on('internalError', function (request, err) { console.log("Internal Error:", err); request.reply.view('errors/500', { error: err }).code(500);}); But my hook never gets called. Is there an easy way to return a custom 500 page with Hapijs?
Now provide the response and nothing else.
| You need to trap the error response inside an onPreResponse extension function and set a new HTML response there. The same principle applies to any Boom error, whether it be one set by you in a handler or set by hapi internally (e.g. a 404 Not found or a 401 Unauthorized from failed auth. Here's an example that you can try yourself: index.js const Hapi = require('hapi');const Path = require('path');const server = new Hapi.Server();server.connection({ port: 4000 });server.route({ method: 'GET', path: '/', handler: function (request, reply) { reply(new Error('I\'ll be a 500')); }});server.ext('onPreResponse', (request, reply) => { if (request.response.isBoom) { const err = request.response; const errName = err.output.payload.error; const statusCode = err.output.payload.statusCode; return reply.view('error', { statusCode: statusCode, errName: errName }) .code(statusCode); } reply.continue();});server.register(require('vision'), (err) => { if (err) { throw err; } server.views({ engines: { hbs: require('handlebars') }, path: Path.join(__dirname, 'templates') }); server.start((err) => { if (err) { throw err; } console.log('Server running at:', server.info.uri); });}); templates/error.hbs <!DOCTYPE html><html lang="en"><head> <meta charset="UTF-8"> <title>{{title}}</title> <style> body { text-align: center; background: #B0B0B0; color: #222; } .error h1 { font-size: 80px; margin-bottom: 0; } </style></head><body> <div class="error"> <h1>⚠<br/>{{statusCode}}</h1> <h2>{{errName}}</h2> </div></body></html> Test it out by going to http://localhost:4000/ to see your custom error page: This approach catches any Boom response, including those generated internally by hapi rather than by us. Therefore will also work with 4xx errors. Try navigating to http://localhost:4000/notapage and you'll get the same pretty page but for a 404: | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/32184744', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1501835/']} | jdg_382622 |
stackexchange | llm_judgeable_groundtruth_similarity | 248168 |
Below is a question asked on the forum security.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
On my Android phone I use several apps that propose biometric authentication. If I enable it, can these applications read my fingerprint data and transfer it to the third party servers?
Now provide the response and nothing else.
| No. Biometrics never leave hardware-backed keystore (TEE). Apps use android Biometric API to authenticate the user. Biometric is verified by hardware-backed keystore which answers authentication result with success or failure to the API. As it's a system API, apps implicitly trust the authentication result. To ensure that it's not a fraudulent TEE verifying the biometrics, you can verify the legitimacy of hardware-backed keystore using hardware-backed key attestation . In app authentication usually protects apps' secrets that are stored inside TEE. Faking the API response by memory corruption will not expose the secrets as TEE doesn't release secrets until user authentication succeeds. | {} | {'log_upvote_score': 5, 'links': ['https://security.stackexchange.com/questions/248168', 'https://security.stackexchange.com', 'https://security.stackexchange.com/users/140184/']} | jdg_382623 |
stackexchange | llm_judgeable_groundtruth_similarity | 30707408 |
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 running Django 1.4.11. I overrode the save() method of a Django model in a way similar to the following code: from django.db import modelsfrom django.db import transactionclass MyModel(models.Model): # model definition @transaction.commit_manually def save(self, *args, **kwargs): try: super(self.__class__, self).save(*args, **kwargs) foo() # do_other_things except: transaction.rollback() raise else: transaction.commit() When I run my code, sometimes I read this message in the Apache log: RemovedInDjango18Warning: commit_manually is deprecated in favor of set_autocommit. How can I implement the same logic with set_autocommit?
Now provide the response and nothing else.
| The same logic would look like this: from django.db import modelsfrom django.db import transactionclass MyModel(models.Model): # model definition def save(self, *args, **kwargs): transaction.set_autocommit(False) try: super(MyModel, self).save(*args, **kwargs) foo() # do_other_things except: transaction.rollback() raise else: transaction.commit() finally: transaction.set_autocommit(True) However, this would be equivalent to using the atomic() decorator: from django.db import modelsfrom django.db import transactionclass MyModel(models.Model): # model definition @transaction.atomic def save(self, *args, **kwargs): super(MyModel, self).save(*args, **kwargs) foo() # do_other_things This will commit the transaction on a successful __exit__ , and roll back in the case of an exception. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/30707408', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/4820341/']} | jdg_382624 |
stackexchange | llm_judgeable_groundtruth_similarity | 2828239 |
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 use Clojure to dynamically generate functions that can be applied to large volumes of data - i.e. a requirement is that the functions be compiled to bytecode in order to execute fast, but their specification is not known until run time. e.g. suppose I specify functions with a simple DSL like: (def my-spec [:add [:multiply 2 :param0] 3]) I would like to create a function compile-spec such that: (compile-spec my-spec) Would return a compiled function of one parameter x that returns 2x+3. What is the best way to do this in Clojure?
Now provide the response and nothing else.
| Hamza Yerlikaya has already made the most important point, which is that Clojure code is always compiled. I'm just adding an illustration and some information on some low-hanging fruit for your optimisation efforts. Firstly, the above point about Clojure's code always being compiled includes closures returned by higher-order functions and functions created by calling eval on fn / fn* forms and indeed anything else that can act as a Clojure function. Thus you don't need a separate DSL to describe functions, just use higher order functions (and possibly macros): (defn make-affine-function [a b] (fn [x] (+ (* a x) b)))((make-affine-function 31 47) 5); => 202 Things would be more interesting if your specs were to include information about the types of parameters, as then you could be interested in writing a macro to generate code using those type hints. The simplest example I can think of would be a variant of the above: (defmacro make-primitive-affine-function [t a b] (let [cast #(list (symbol (name t)) %) x (gensym "x")] `(fn [~x] (+ (* ~(cast a) ~(cast x)) ~(cast b)))))((make-primitive-affine-function :int 31 47) 5); => 202 Use :int , :long , :float or :double (or the non-namespace-qualified symbols of corresponding names) as the first argument to take advantage of unboxed primitive arithmetic appropriate for your argument types. Depending on what your function's doing, this may give you a very significant performance boost. Other types of hints are normally provided with the #^Foo bar syntax ( ^Foo bar does the same thing in 1.2); if you want to add them to macro-generated code, investigate the with-meta function (you'll need to merge '{:tag Foo} into the metadata of the symbols representing the formal arguments to your functions or let -introduced locals that you wish to put type hints on). Oh, and in case you'd still like to know how to implement your original idea... You can always construct the Clojure expression to define your function -- (list 'fn ['x] (a-magic-function-to-generate-some-code some-args ...)) -- and call eval on the result. That would enable you to do something like the following (it would be simpler to require that the spec includes the parameter list, but here's a version assuming arguments are to be fished out from the spec, are all called paramFOO and are to be lexicographically sorted): (require '[clojure.walk :as walk])(defn compile-spec [spec] (let [params (atom #{})] (walk/prewalk (fn [item] (if (and (symbol? item) (.startsWith (name item) "param")) (do (swap! params conj item) item) item)) spec) (eval `(fn [~@(sort @params)] ~@spec))))(def my-spec '[(+ (* 31 param0) 47)])((compile-spec my-spec) 5); => 202 The vast majority of the time, there is no good reason to do things this way and it should be avoided; use higher-order functions and macros instead. However, if you're doing something like, say, evolutionary programming, then it's there, providing the ultimate flexibility -- and the result is still a compiled function. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/2828239', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/214010/']} | jdg_382625 |
stackexchange | llm_judgeable_groundtruth_similarity | 40786220 |
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 develop .net core app and use NLog as logging framework. How can I setup NLog layout to get remote IP address? Unfortunately, ${aspnet-request.serverVariable=remote_addr} isn't supported by NLog.Web.AspNetCore . May be I can get access to httpContext.Connection.RemoteIpAddress somehow.
Now provide the response and nothing else.
| This is supported since NLog.Web.AspNetCore 4.4.0. Install the package NLog.Web.AspNetCore Set in your config <!-- enable asp.net core layout renderers --><extensions> <add assembly="NLog.Web.AspNetCore"/></extensions> You could now use ${aspnet-request-ip} in your config. PS: also supported for ASP.NET in NLog.Web 4.5.0 Old answer Currently this is not supported, but you could inject it in NLog like this: using System;using System.Text;using Microsoft.AspNetCore.Http;using NLog.Config;using NLog.LayoutRenderers;using NLog.Web.Internal;namespace NLog.Web.LayoutRenderers{ /// <summary> /// Render the request IP for ASP.NET Core /// </summary> /// <example> /// <code lang="NLog Layout Renderer"> /// ${aspnet-request-ip} /// </code> /// </example> [LayoutRenderer("aspnet-request-ip")] public class AspNetRequestIpLayoutRenderer : AspNetLayoutRendererBase { protected override void DoAppend(StringBuilder builder, LogEventInfo logEvent) { var httpContext = HttpContextAccessor.HttpContext; if (httpContext == null) { return; } builder.Append(httpContext.Connection.RemoteIpAddress); } }} Register it (startup.cs) ConfigurationItemFactory.Default.LayoutRenderers .RegisterDefinition("aspnet-request-ip", typeof(AspNetRequestIpLayoutRenderer)); See also Extending NLog usage ${aspnet-request-ip} Also include NLog.Web.AspNetCore! | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/40786220', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/5525734/']} | jdg_382626 |
stackexchange | llm_judgeable_groundtruth_similarity | 13202905 |
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 a new at Zendframework 2. I am trying to join two tables and display the result. The two tables are. Works and Artist . The tables are joined based on artist_id. STEP 1> Created 2 class(Works , Artist) in ModelSTEP 2> In WorksTable I have the following code class WorksTable extends AbstractTableGateway{ protected $table ='works'; public function __construct(Adapter $adapter) { $this->adapter = $adapter; $this->resultSetPrototype = new HydratingResultSet( new ArraySerializableHydrator(), new Works() ); $this->resultSetPrototype->buffer(); $this->initialize(); } public function fetchAll() { $select = $this->getSql()->select(); $select->join('works','artists.artist_id = artist_id '); //create paginator object to display records $paginator = new Paginator( new DbSelect($select, $this->adapter, $this->resultSetPrototype) ); return $paginator; }} STEP 3> In controller I defined the following code public function searchAction() { $request = $this->getRequest(); $paginator = $this->getWorksTable()->fetchAll(); // $paginator->setItemCountPerPage(12); $vm = new ViewModel(array( 'poster' => $paginator, )); $vm->setVariable('paginator', $paginator); return $vm; } For statement $paginator->setItemCountPerPage(12); get error Message: SQLSTATE[42000]: Syntax error or access violation: 1066 Not unique table/alias: 'works' Has anyone come across this error? Any ideas on how to resolve this?
Now provide the response and nothing else.
| The contextMenus API is used to define context menu entries. It does not need to be called right before a context menu is opened. So, instead of creating the entries on the contextmenu event, use the selectionchange event to continuously update the contextmenu entry. I will show a simple example which just displays the selected text in the context menu entry, to show that the entries are synchronized well. Use this content script: document.addEventListener('selectionchange', function() { var selection = window.getSelection().toString().trim(); chrome.runtime.sendMessage({ request: 'updateContextMenu', selection: selection });}); At the background, we're going to create the contextmenu entry only once. After that, we update the contextmenu item (using the ID which we get from chrome.contextMenus.create ). When the selection is empty, we remove the context menu entry if needed. // ID to manage the context menu entryvar cmid;var cm_clickHandler = function(clickData, tab) { alert('Selected ' + clickData.selectionText + ' in ' + tab.url);};chrome.runtime.onMessage.addListener(function(msg, sender, sendResponse) { if (msg.request === 'updateContextMenu') { var type = msg.selection; if (type == '') { // Remove the context menu entry if (cmid != null) { chrome.contextMenus.remove(cmid); cmid = null; // Invalidate entry now to avoid race conditions } // else: No contextmenu ID, so nothing to remove } else { // Add/update context menu entry var options = { title: type, contexts: ['selection'], onclick: cm_clickHandler }; if (cmid != null) { chrome.contextMenus.update(cmid, options); } else { // Create new menu, and remember the ID cmid = chrome.contextMenus.create(options); } } }}); To keep this example simple, I assumed that there's only one context menu entry. If you want to support more entries, create an array or hash to store the IDs. Tips Optimization - To reduce the number of chrome.contextMenus API calls, cache the relevant values of the parameters. Then, use a simple === comparison to check whether the contextMenu item need to be created/updated. Debugging - All chrome.contextMenus methods are asynchronous. To debug your code, pass a callback function to the .create , .remove or .update methods. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/13202905', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1795410/']} | jdg_382627 |
stackexchange | llm_judgeable_groundtruth_similarity | 350953 |
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'm trying to build a circuit that realizes the transfer function:$$ V_o = 0.33V_i + 1.65V$$ Using what I know about voltage dividers and resistive adders, I built: simulate this circuit – Schematic created using CircuitLab but this is giving me an output much closer to:$$V_o = 0.2V_i + 1V$$ Where am I going wrong?
Now provide the response and nothing else.
| There are two problems with your design. A voltage divider only produces it's notional output voltage when unloaded. Your second stage forms an averaging circuit not a sum. Bottom line is that your approach isn't going to be fruitful. Fortunately a much simpler design will solve your problem. We just need a weighted average circuit. For ease of calculation i'm going to assume that when you wrote 0.33 you meant \$\frac{1}{3}\$ if you want to actually use 0.33 that makes the numerics less nice but does'nt change the principles. We can rewrite your equation as a weighted average and implement it as a weighted average circuit. This consists of three resistors, one from the input to the output, one from 3.3V to the output and one from ground to the output. $$V_o = \frac{1}{3}V_i + 1.65 = \frac{2}{6}V_i + \frac{3}{6}3.3+\frac{1}{6}0$$ (note that our weights add up to 1 and all of them are positive, that is important) Now we simply take the reciprocal of the weights to work out our resistor values. $$R_{Vi} = \frac{6}{2}R$$$$R_{3.3V} = \frac{6}{3}R$$$$R_{Ground} = \frac{6}{1}R$$ Where \$R\$ is the output impedance of our weighted average circuit. Then it becomes a matter of picking a \$R\$ value to set the actual value of our resistors. Ideally we want to pick it such that all three values are standard values. Turns out that \$R=0.5\mathrm{k}\Omega\$ works out nicely giving us. $$R_{Vi} = \frac{6}{2}R = 1.5\mathrm{k}\Omega$$$$R_{3.3V} = \frac{6}{3}R = 1\mathrm{k}\Omega$$$$R_{Ground} = \frac{6}{1}R = 3\mathrm{k}\Omega$$ | {} | {'log_upvote_score': 4, 'links': ['https://electronics.stackexchange.com/questions/350953', 'https://electronics.stackexchange.com', 'https://electronics.stackexchange.com/users/127757/']} | jdg_382628 |
stackexchange | llm_judgeable_groundtruth_similarity | 2817664 |
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 XSL template that is selected for execution (below). What I would like to do is be able to tell if I am the last Unit being matched. <xsl:template match="Unit[@DeviceType = 'Node']"> <!-- Am I the last Unit in this section of xml? --> <div class="unitchild"> Node: #<xsl:value-of select="@id"/> </div> </xsl:template> Example XML <Unit DeviceType="QueueMonitor" Master="1" Status="alive" id="7"> <arbitarytags /> <Unit DeviceType="Node" Master="0" Status="alive" id="8"/> <Unit DeviceType="Node" Master="0" Status="alive" id="88"/></Unit>
Now provide the response and nothing else.
| The currently selected answer is generally incorrect! <xsl:if test="not(following-sibling::Unit)"> This Will not work with any XML document and any <xsl:apply-templates> The original question is about the last Unit being matched, not the last sibling! Which is the last Unit being matched depends only on the expression in the select attribute of <xsl:apply-templates> , not on the physical properties of the XML document. The way to do it : <xsl:apply-templates select="SomeExpression"/> then in the template that matches nodes selected by SomeExpression : <xsl:if test="position() = last()">. . . . </xsl:if> This checks if the current node is the last in the node-list selected by <xsl:apply-templates> , not that the current node is the last sibling . This answers exactly the original question. If the question was framed in a different way, asking how to recognize if the last sibling Unit is the current node, then the best solution would be to specify a separate template for this last sibling node: <xsl:template match="Unit[last()]"> . . . . </xsl:template> Do note , that in this case there is no need to write any conditional logic inside a template to test if the current node is "the last". | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/2817664', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/94278/']} | jdg_382629 |
stackexchange | llm_judgeable_groundtruth_similarity | 1199630 |
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:
Let $F$ be a field containing $\mathbb R$ with the property that $\dim_{\mathbb R}F < \infty.$ Then either $F \cong \mathbb R$ or $F \cong \mathbb C.$ I am trying to prove the above statement. I am not supposed to use Frobenius' theorem as it would just spoil the spirit of the current problem. I am told to show that every $x \in F \setminus \mathbb R$ is a root of some non-zero polynomial in $F[x]$ with leading coefficient $1$ and some other things. But I am not really been able to prove anything so far. Please help. Thanks in advance.
Now provide the response and nothing else.
| By the uniqueness of the algebraic closure, we have an embedding $F \hookrightarrow \mathbb C$, hence we have $\mathbb R \subset F \subset \mathbb C$. The result follows from $[\mathbb C:\mathbb R]=2$, because this excludes the existence of proper intermediate fields. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/1199630', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/-1/']} | jdg_382630 |
stackexchange | llm_judgeable_groundtruth_similarity | 3412 |
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:
Just need a little help with the GatherBy / SplitBy function(s). I have a list of random numbers here: {8, 4, 2, 1, 9, 4, 2, 1, 5, 2, 1, 3, 1, 2, 11, 4, 2, 1, 5, 2, 1, 3, \1, 2, 7, 2, 1, 3, 1, 2, 5, 1, 2, 4, 15, 4, 2, 1, 5, 2, 1, 3, 1, 2, 7, \2, 1, 3, 1, 2, 5, 1, 2, 4, 11, 2, 1, 3, 1, 2, 5, 1, 2, 4, 9, 1, 2, 4, 8} How can I write a function with a look-ahead? I want to gather the numbers so it splits whenever it the next number is larger than the current one? (spaced for clarity): {{8, 4, 2, 1},{9, 4, 2, 1},{5, 2, 1},{3, 1},{2},{11, 4, 2, 1},...} Tried and failed: SplitBy[%, Greater]
Now provide the response and nothing else.
| You need Split : Split[list, Greater] SplitBy doesn't work here because the specified function is applied to each element separately before doing a normal Split . What you want is a pair-wise comparison with a custom comparator, which is what Split does. Looking at this again you may want GreaterEqual to group identical elements in the same list: Split[{2, 1, 1, 7, 5, 5, 5, 6, 0}, GreaterEqual] {{2, 1, 1}, {7, 5, 5, 5}, {6, 0}} For fun I tried to do this operation without Split . Since I was having fun I used Do rather than Module to localize symbols i and x . split = Last @ Reap @ Do[If[n > x, i++]; Sow[x = n, i], {i, 1}, {x, 1}, {n, #}] &;split @ {2, 1, 1, 7, 5, 5, 5, 6, 0} {{2, 1, 1}, {7, 5, 5, 5}, {6, 0}} | {} | {'log_upvote_score': 5, 'links': ['https://mathematica.stackexchange.com/questions/3412', 'https://mathematica.stackexchange.com', 'https://mathematica.stackexchange.com/users/487/']} | jdg_382631 |
stackexchange | llm_judgeable_groundtruth_similarity | 194857 |
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 wondering what are the best practices regarding if/then/else ; I tend to use the following form (because I find it easier to read) #!/usr/bin/ksh#[[ -f /path/to/target/file ]] && { echo "File exists"} || { echo "No such file"} instead of this form #!/usr/bin/ksh#if [ -f /path/to/target/file ] ; then echo "File exists"else echo "No such file"fi I also include a true statement just before } || { for complex block, to ensure that "else" part will not be executed. What are your recommendations ?
Now provide the response and nothing else.
| The problem with that style is that the two forms aren't equivalent. When you use: if command; then fooelse barfi then either foo or bar will be called, never both. When using both && and || , both paths can be taken: $ [[ -d / ]] && {> echo "Path 1 taken"> false> } || {> echo "Path 2 taken"> }Path 1 takenPath 2 taken$ When using the if cmd; then foo; else bar; fi form, the condition for bar being called is cmd returning false. When using the cmd && foo || bar form, the condition for bar being called is cmd && foo returning false. EDIT: I just noticed that in your question you acknowledge that you need to put true at the end of blocks to make your version work at all. If you're willing to do that, I'm not aware of any other major issues - but I'd argue that a style that requires you to unconditionally add "true" as the last command in a block if there's any possibility that the previous command could fail just guarantees that you'll eventually forget it, and things will look like they're working correctly until they don't. | {} | {'log_upvote_score': 4, 'links': ['https://unix.stackexchange.com/questions/194857', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/109481/']} | jdg_382632 |
stackexchange | llm_judgeable_groundtruth_similarity | 769374 |
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 trying to setup an IPv6 web-server on CentOS 7.2 with NGINX. I have tested my IPv6 connectivity outgoing and incoming - everything works. My IP, AAAA records, etc as fine as well. Essentially everything is OK until I enable FirewallD. I have it set up to default to the drop zone with eth0 interface. I have enabled dhcpv6-client, http, https and ssh (ssh is on a custom port). When the firewall is enabled no IPv6 traffic can leave or enter the machine. Traceroute6 to anything (even the gateway) only goes to localhost. If I disable the firewall, it's all good. I have no idea why this is happening. I couldn't find anything online in order to make FirewallD apply the same IPv4 config to the IPv6 traffic. I personally thought, it would do that automatically, as all of its commands are IP protocol agnostic. Any help is much appreciated.
Now provide the response and nothing else.
| I ran into the same issue. After following the logic through the rules that firewalld puts in I found that the drop zone was blocking ipv6 icmp that is needed to find the ipv6 neighbors. There is a rule to allow all ipv6 icmp but firewalld puts it after the input zones which is where the drop rules go. If you want to see this for yourself just look at the output from 'ip6tables -L -n -v' So, a quick and dirty fix is to do this: firewall-cmd --permanent --direct --add-rule ipv6 filter INPUT 0 -p icmpv6 -j ACCEPT Firewalld puts the direct rules before the other input rules so that will happen before the drop rules. If you want to block things like ping you would also use a direct rule but you would need it before the rule above. You would do something like: firewall-cmd --permanent --direct --add-rule ipv6 filter INPUT 0 -p icmpv6 --icmpv6-type 128 -j DROPfirewall-cmd --permanent --direct --add-rule ipv6 filter INPUT 1 -p icmpv6 -j ACCEPT The priorities will keep them in order. | {} | {'log_upvote_score': 4, 'links': ['https://serverfault.com/questions/769374', 'https://serverfault.com', 'https://serverfault.com/users/241670/']} | jdg_382633 |
stackexchange | llm_judgeable_groundtruth_similarity | 17605 |
Below is a question asked on the forum mathoverflow.net. Provide a good and informational response to it like a helpful human would.
Question:
I found the following equation on some web page I cannot remember, and found it interesting: $$f(f(x))=\cos(x)$$ Out of curiosity I tried to solve it, but realized that I do not have a clue how to approach such an iterative equation except for trial and error. I also realized that the solution might not be unique, from the solution of a simpler problem $$f(f(x)) = x$$ which has, for example, solutions $f(x) = x$ and $f(x) = \frac{x+1}{x-1}$ . Is there a general solution strategy to equations of this kind? Can you perhaps point me to some literature about these kind of equations? And what is the solution for $f(f(x))=\cos(x)$ ?
Now provide the response and nothing else.
| There are no continuous solutions. Since the cosine has a unique fixed point $x_0$ (such that $\cos x_0=x_0$ ), it should be a fixed point of $f$ . And f should be injective and hence monotone (increasing or decreasing) in a neighborhood of $x_0$ . Then $f(f(x))$ is increasing in a (possibly smaller) neighborhood of $x_0$ while the cosine is not. As for discontinuous ones, there are terribly many of them ( $2^{\mathbb R}$ ) and you probably cannot parametrize them in any reasonable way. You can describe them in terms of orbits of iterations of $\cos x$ , but I doubt this would count as a solution of the equation. UPDATE: Here is how to construct a solution (this is technical and I might overlook something). Let X be an infinite set and $g:X\to X$ is a map, I am looking for a sufficient conditions for the existence of a solution of $f\circ f=g$ . Define the following equivalence relation on $X$ : $x$ and $y$ are equivalent iff $g^n(x)=g^m(y)$ for some positive integers $m$ and $n$ . Equivalence classes will be referred to as orbits (the term is wrong but I don't know what is a correct one). Two orbits are said to be similar is there is a bijection between them commuting with $g$ . If $Y$ and $Z$ are two similar orbits, one can define $f$ on $Y\cup Z$ as follows: on $Y$ , $f$ is that bijection to $Z$ , and on $Z$ , $f$ is the inverse bijection composed with $g$ . So if the orbits can be split into pairs of similar ones, we have a desired $f$ . Now remove from the real line the fixed point of cos and all its roots ( $\pi/2$ and the like). Then, if I am not missing something, in the remaining set $X$ all orbits of $\cos$ are similar, so we can define $f$ as above. Define $f$ so that $0$ has a nonempty pre-image (that is, the orbit containing $0$ should be used as $Z$ and not as $Y$ ). Finally, map the fixed point of $\cos$ to itself, and the roots of $\cos$ to some pre-image of $0$ . | {} | {'log_upvote_score': 6, 'links': ['https://mathoverflow.net/questions/17605', 'https://mathoverflow.net', 'https://mathoverflow.net/users/4503/']} | jdg_382634 |
stackexchange | llm_judgeable_groundtruth_similarity | 1699882 |
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:
$W(n)$ is the function that counts number of distinct prime divisors of $n$. I have been able to prove for any $m$ consecutive integers starting with $1+a$ with the condition $a\leq (m^2-4m)/4$ , there exist a number $n$ in that sequence with the property $W(n)\leq 2$. Is it worth to publishing? Is it some thing new?
Now provide the response and nothing else.
| Short answer: no, don't publish this. If you want to publish anything, you should first make sure you've stated the theorem properly. As has been discussed in the comments, the theorem was a little unclear. But you've explained what theorem you actually meant, so let's state it once more to avoid any confusion. Option 1. For any integer $m>4$, there exists a sequence of $m$ consecutive integers such that at least one number in that sequence has at most $2$ distinct prime factors. This is trivial: I can give you any sequence starting at a prime, for example, $$23,24,\cdots,23+m-1$$ and that is such a sequence (since the first number of the sequence, in this case, $23$, has $\omega(23)=1$). However, let's state the other two options here. Option 2. For any integer $m>4$, there exists a sequence of $m$ consecutive integers all having at most $2$ distinct prime factors. or Option 3. For any sequence of $m>4$ consecutive integers, there is a number in that sequence with at most $2$ prime factors. The third option is disproved by MooS and Patrick Stevens by counterexamples (see MooS's answer or Patrick Stevens' comment). Option 2 is also disproved by Patrick Stevens, by cleverly noting that any sequence of $30$ consecutive integers contains at least one multiple of $30$, and so at least one number in that sequence has at least $3$ prime factors. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/1699882', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/316730/']} | jdg_382635 |
stackexchange | llm_judgeable_groundtruth_similarity | 57427 |
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 am a network admin at a high school in South Africa, running on a Microsoft network. We have approximately 150 PCs around the campus, of which at least 130 are wired to the network. The remaining are staff laptops. All IP addresses are assigned using a DHCP server. Currently, our wi-fi access is limited to a few locations where those staff are located. We're using WPA with a long key which is not made available to students. To my knowledge, this key is safe. It would make more sense, however, to use RADIUS authentication but I have some questions about how it works in practice. Will machines that are added to the domain authenticate automatically to the wi-fi network? Or is it user-based? Can it be both? Will devices like a PSP / iPod touch / Blackberry / etc / be able to connect to the WiFi network if it uses RADIUS authentication? I would want this to happen. I do have WAPs that support RADIUS authentication. I would just need to turn the RADIUS functionality on from a MS 2003 Server. Given the mobile-device requirement, would using a captive-portal be better? I know from experience in airports that it can be done (if the device has a browser). Which brings me to questions regarding Captive portals: Can I limit the captive portal to Wi-Fi connected devices only? I don't particularly want to have to set up MAC address exceptions for all existing network machines (in my understanding, it just increases the opportunity for MAC address spoofing). How is this done? Do I have a separate address range for WiFi access devices and then will the captive portal route between the two networks? It is important to emphasise that the WAPs share a physical network with other machines that are not to be captive-portalled. Your experience and insight will be appreciated! Philip Edit: In order to get a little more clarity on whether a Captive Portal is even feasible, I've asked this question .
Now provide the response and nothing else.
| User authentification for Wifi use 802.1x protocol. To connect devices need a WPA supplicant such as SecureW2 Depending of the supplicant you use you will or not will be able to use do a SSO with the windows domain login/password. iPhone and iPod touch have built in WPA supplicant. I don't know for PSP/BB. SecureW2 has a Windows Mobile version. I'm sure that you could enable a captive portal for WiFi only without having to create to IP Network. You just need to put wireless access in a vlan and wired access in another vlan then put the portal between both vlan. This is like a transparent firewall. 802.1x need to have a supplicant on computers. If computers that need to use the Wifi are known you just have to setup the supplicant on them and it's a great solution. If you want to make your wireless access accessible by visitor or things like that it could be a nightmare because they need the supplicant etc.. A captive portal is a bit less secure and need user to authenticate manually each time they connect. It can be a bit borring. A good solution from my point of view is too have both. A 802.1x access that give you the same as if you were wired on the lan and a captive portal that give you access to less things (access to internet port 80, limited access to local lan, ...) | {} | {'log_upvote_score': 4, 'links': ['https://serverfault.com/questions/57427', 'https://serverfault.com', 'https://serverfault.com/users/6442/']} | jdg_382636 |
stackexchange | llm_judgeable_groundtruth_similarity | 209982 |
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:
In working with python for the first time, I've found that I end up writing multiple classes in the same file, which is opposed to other languages like Java, which uses one file per class. Usually, these classes are made up of 1 abstract base class, with 1-2 concrete implementations who's use varies slightly. I've posted one such file below: class Logger(object): def __init__(self, path, fileName): self.logFile = open(path + '/' + filename, 'w+') self.logFile.seek(0, 2) def log(self, stringtoLog): self.logFile.write(stringToLog) def __del__(self): self.logFile.close()class TestLogger(Logger): def __init__(self, serialNumber): Logger.__init__('/tests/ModuleName', serialNumber): def readStatusLine(self): self.logFile.seek(0,0) statusLine = self.logFile.readLine() self.logFile.seek(0,2) return StatusLine def modifyStatusLine(self, newStatusLine): self.logFile.seek(0,0) self.logFile.write(newStatusLine) self.logFile.seek(0,2) class GenericLogger(Logger): def __init__(self, fileName): Logger.__init__('/tests/GPIO', fileName): def logGPIOError(self, errorCode): self.logFile.write(str(errorCode)) As seen above, I have a Logger base class, with a couple of implementation differences below that. The Question: Is this standard for python, or for any language? What problems could arise from using this implementation if any? Please note: I'm not really looking for guidance on this specific file, but in a more general sense. What if the classes ended up being 3-5 moderately complex methods? Would it make sense to split them then? Where is the cutoff for saying you should split a file up?
Now provide the response and nothing else.
| It's fine. It's fine in C++ as well, for reference. Keeping tightly-coupled things together is sensible practice. Avoiding inappropriate coupling is also good practice. Striking the right balance isn't a matter of strict rules, but of, well, striking a balance between different concerns. Some rules of thumb: Size Excessively large files can be ugly, but that's hardly the case here. Ugliness is probably a good enough reason to split a file, but developing that aesthetic sense is largely a matter of experience, so it doesn't help you figure out what to do a priori Separation of Concerns If your concrete implementations have very different internal concerns, your single file accumulates all those concerns. For example, implementations with non-overlapping dependencies make your single file depend on the union of all those dependencies. So, it might sometimes be reasonable to consider the sub-classes' coupling to their dependencies outweighs their coupling to the interface (or conversely, the concern of implementing an interface is weaker than the concerns internal to that implementation). As a specific example, take a generic database interface. Concrete implementations using an in-memory DB, an SQL RDBMS and a web query respectively may have nothing in common apart from the interface, and forcing everyone who wants the lightweight in-memory version to also import an SQL library is nasty. Encapsulation Although you can write well-encapsulated classes in the same module, it could encourage unnecessary coupling just because you have access to implementation details that wouldn't otherwise be exported outside the module. This is just poor style I think, but you could enforce better discipline by splitting the module if you really can't break the habit. | {} | {'log_upvote_score': 6, 'links': ['https://softwareengineering.stackexchange.com/questions/209982', 'https://softwareengineering.stackexchange.com', 'https://softwareengineering.stackexchange.com/users/93290/']} | jdg_382637 |
stackexchange | llm_judgeable_groundtruth_similarity | 29202277 |
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 spring-data's repositories - very convenient thing but I faced an issue. I easily can update whole entity but I believe it's pointless when I need to update only a single field: @Entity@Table(schema = "processors", name = "ear_attachment")public class EARAttachment { private Long id; private String originalName; private String uniqueName;//yyyy-mm-dd-GUID-originalName private long size; private EARAttachmentStatus status; to update I just call method save. In log I see the followwing: batching 1 statements: 1: update processors.ear_attachment set message_id=100, original_name='40022530424.dat', size=506, status=2,unique_name='2014-12-16-8cf74a74-e7f3-40d8-a1fb-393c2a806847-40022530424.dat'where id=1 I would like to see some thing like this: batching 1 statements: 1: update processors.ear_attachment set status=2 where id=1 Spring's repositories have a lot of facilities to select something using name conventions, maybe there is something similar for update like updateForStatus(int status);
Now provide the response and nothing else.
| You can try something like this on your repository interface: @Modifying@Query("update EARAttachment ear set ear.status = ?1 where ear.id = ?2")int setStatusForEARAttachment(Integer status, Long id); You can also use named params, like this: @Modifying@Query("update EARAttachment ear set ear.status = :status where ear.id = :id")int setStatusForEARAttachment(@Param("status") Integer status, @Param("id") Long id); The int return value is the number of rows that where updated. You may also use void return. See more in reference documentation. | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/29202277', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1004374/']} | jdg_382638 |
stackexchange | llm_judgeable_groundtruth_similarity | 25067224 |
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 mimic the behavior of overflow-y:hidden to overflow-x , but it doesn't behave the same way. overflow-x:hidden doesn't allow to scroll (by dragging the mouse). See: http://jsfiddle.net/Gxm2z/ #container { width: 300px}#modules { height: 50px; padding: 5px; white-space: nowrap; overflow-y: hidden; overflow-x: scroll; -webkit-overflow-scrolling: touch;}.module { display: inline-block; width: 50px; height: 50px; line-height: 50px; text-align: center; background: #ddd;} How can I achieve the same result without a scroll bar? I'm ok with a javascript/jQuery plugin. The plan is to use arrows, and maybe a custom scrollbar
Now provide the response and nothing else.
| this is my solution CSS based - simple and nice on all devices, no need for additional JS. add fixed height and overflow hidden to parent element (in your case #container ) enlarge height of #modules - this create enough place hidden under parent element for scrollbar (because of smaller #container height, this place is invisible) using -webkit-overflow-scrolling:touch; is good choice, make nice behavior on iPad and iPhone #container { width: 300px; height: 60px; overflow: hidden;}#modules { height: 90px; /* 40px - more place for scrollbar, is hidden under parent box */ padding: 5px; white-space: nowrap; overflow-x: scroll; overflow-y: hidden; -webkit-overflow-scrolling: touch;} live demo: http://jsfiddle.net/s6wcudua/ | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/25067224', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1732521/']} | jdg_382639 |
stackexchange | llm_judgeable_groundtruth_similarity | 178118 |
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 dedicated server with one network card in it. I however got two IP addresses. When I use the simple command sudo ip addr add 188.40.90.88 dev eth0 it fails to see it as a separate IP. I've googled along trying to find a fix, but I can't really find out what packages I need to set up a switch, and how to do it. My dedicated server runs with the following specifications: 16GB DDR3 RAM ( intel i7 ) OS: ubuntu 14.01 These are the two most important ones, I believe; I've got no idea what network card my dedicated server has, but I know it supports IEEE 802.1q , which I found out on the Ubuntu website.
Now provide the response and nothing else.
| I'm not quite sure exactly what you're trying to accomplish. I am assuming that your question could be re-titled "How to set up two IPs on a single network interface." Each network interface on your machine is given an identifier. Typically, you start with eth0 and work your way up (eth1, eth2, eth3). These are all physically different network cards. You can also have virtual cards on top of each of your physical cards. This is how you would set up multiple IPs on the same NIC. To set this up, you can use the following example, changing the addresses to suit your needs ( /etc/network/interfaces ): # This file describes the network interfaces available on your system# and how to activate them. For more information, see interfaces(5).# The loopback network interfaceauto loiface lo inet loopback# The primary network interfaceauto eth0 eth0:0allow-hotplug eth0 eth0:0#eth0iface eth0 inet staticaddress 123.123.123.123netmask 255.255.255.0gateway 123.123.123.1#eth0:0 (LAN)iface eth0:0 inet staticaddress 212.212.212.212netmask 255.255.128.0gateway 212.212.212.1 The tricky part could be the netmask. Try 255.255.255.0 if you aren't sure. | {} | {'log_upvote_score': 5, 'links': ['https://unix.stackexchange.com/questions/178118', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/85043/']} | jdg_382640 |
Subsets and Splits