Local ipv6 route is always in the global prefix, assuming that it's standard /64 prefix. So:

ip -6 route show | grep -v fe80 | awk '{print $1}'

2001:8a0:e4b3:e800::/64

Removed local (ULA) addresses using grep -v fe80. I changed my prefix to some random.

If your prefix is not /64 and you are using SLAAC, you'll still get /64 local route.

I just want to drop here, that angular supports using javascript string-interpolation since 19.2.0 (untagged template literals).

define car and array. you should be able get a callable and return at the end. as long you don't want to return an undefined array. KiSs <3

Yet another workaround is to set WA_TransparentForMouseEvents attribute to child widget of QVideoWidget:

 QWidget *c = findChild<QWidget*>();
 if (c)
     c->setAttribute(Qt::WA_TransparentForMouseEvents);

We had this exact same behavior when we put in an intro file with different bitrate and stereo/mono settings than the stream. The file would play and then the stream would not play. Interesting though, it played on our mobile app, but not in the browser.

We fixed the bitrate and stereo problem and now it plays fine.

Just install django-oscar version 3.2.4 as follows:

pip install django-oscar[sorl-thumbnail]==3.2.4

and problem was solved.

Great solution for automating workflows in Google Sheets! If you're looking to learn how to build custom scripts to loop through stock spreadsheets efficiently, I highly recommend checking out this detailed article: Google Sheets Script – Loop Through Stocks Spreadsheet. It offers a clear step-by-step guide, perfect for both beginners and those with some experience in Google Apps Script.

I made a unit for you to do this:

unit DeviceLister;

interface

uses
  System.Classes
  ,System.SysUtils
  {$IFDEF MSWINDOWS}
  ,Winapi.Windows
  {$ENDIF};

function GetPluggedInDevices: TStringList;

implementation

{$IFDEF MSWINDOWS}
const
  DIGCF_PRESENT = $00000002;
  DIGCF_ALLCLASSES = $00000004;
  SPDRP_DEVICEDESC = $00000000;

type
  HDEVINFO = Pointer;
  ULONG_PTR = NativeUInt;

  TSPDevInfoData = packed record
    cbSize: DWORD;
    ClassGuid: TGUID;
    DevInst: DWORD;
    Reserved: ULONG_PTR;
  end;

function SetupDiGetClassDevsW(ClassGuid: PGUID; Enumerator: PWideChar; hwndParent: HWND;
  Flags: DWORD): HDEVINFO; stdcall; external 'setupapi.dll' name 'SetupDiGetClassDevsW';

function SetupDiEnumDeviceInfo(DeviceInfoSet: HDEVINFO; MemberIndex: DWORD;
  var DeviceInfoData: TSPDevInfoData): BOOL; stdcall; external 'setupapi.dll';

function SetupDiGetDeviceRegistryPropertyW(DeviceInfoSet: HDEVINFO;
  const DeviceInfoData: TSPDevInfoData; Property_: DWORD; var PropertyRegDataType: DWORD;
  PropertyBuffer: PBYTE; PropertyBufferSize: DWORD; RequiredSize: PDWORD): BOOL; stdcall; external 'setupapi.dll' name 'SetupDiGetDeviceRegistryPropertyW';

function SetupDiDestroyDeviceInfoList(DeviceInfoSet: HDEVINFO): BOOL; stdcall; external 'setupapi.dll';
{$ENDIF}

function GetPluggedInDevices: TStringList;
{$IFDEF MSWINDOWS}
var
  DeviceInfoSet: HDEVINFO;
  DeviceInfoData: TSPDevInfoData;
  i: Integer;
  DeviceName: array[0..1023] of Byte;
  RegType: DWORD;
{$ENDIF}
begin
  Result := TStringList.Create;

  {$IFDEF MSWINDOWS}
  DeviceInfoSet := SetupDiGetClassDevsW(nil, nil, 0, DIGCF_ALLCLASSES or DIGCF_PRESENT);
  if NativeUInt(DeviceInfoSet) = NativeUInt(INVALID_HANDLE_VALUE) then
  begin
    Result.Add('Failed to get device list.');
    Exit;
  end;

  i := 0;
  DeviceInfoData.cbSize := SizeOf(TSPDevInfoData);

  while SetupDiEnumDeviceInfo(DeviceInfoSet, i, DeviceInfoData) do
  begin
    if SetupDiGetDeviceRegistryPropertyW(DeviceInfoSet, DeviceInfoData, SPDRP_DEVICEDESC,
      RegType, @DeviceName, SizeOf(DeviceName), nil) then
    begin
      Result.Add(Format('%d: %s', [i + 1, PWideChar(@DeviceName)]));
    end;
    Inc(i);
  end;

  SetupDiDestroyDeviceInfoList(DeviceInfoSet);
  {$ELSE}
  Result.Add('Device listing is only supported on Windows.');
  {$ENDIF}
end;

end.

And then in your app, you can simply add DeviceLister to your uses list, and then call the GetPluggedInDevices function. Here's an example where I'm calling and using it on a button to display the devices onto a memo:

procedure TForm1.Button1Click(Sender: TObject);
begin
  var Devices := GetPluggedInDevices;
  Memo1.Lines.Assign(Devices);
  Devices.Free;
end;

And the result:

Is this kind of what you wanted?

Turns out it is a bug in PyCharm: https://youtrack.jetbrains.com/issue/PY-60819/FLASKDEBUG1-breaks-debugger-when-Python-PyCharm-installation-path-has-spaces#focus=Comments-27-8071749.0-0

Looks like it was fixed in the 2025.2.0 release.

I upgraded to 2025.2 and can confirm that the issue has been resolved.

Using a Google Business Profile for your business on Google Maps can be beneficial, but for businesses functioning within multiple cities, relying solely on Google's geocomplete-based listings is counterproductive.

Google Maps tends to restrict visibility to a particular local area radius, meaning your business would not show up in searches outside of your immediate vicinity.

This is where business directories focused on a particular state, like EZ Local, shine.

EZ Local, unlike Google geocomplete, empowers businesses to list in multiple cities, even across state lines, thus broadening their reach. Contractors, service providers, or companies with a statewide footprint needing untethered, local exposure can greatly benefit from EZ Local.

If your business would like to reach beyond neighborhood customers, such targeting with EZ Local becomes scalable and more SEO-friendly.

From Igor Tandetnik:

cppreference has this to say: (1) a consteval specifier implies inline; and (2) The definition of an inline function must be reachable in the translation unit where it is accessed. I'm 99% sure you won't be able to hide the definition of consteval function in the library; you'd have to put it into the header.

To ensure if that setup is valid or possible, it would be best to consult a Google Cloud sales specialist. They can offer personalized advice and technical recommendations tailored to your application’s needs. From identifying suitable use cases to helping you manage future workload costs effectively, their insights can be invaluable.

you most likely have a framework or css folder overriding the table row element's end. it's changing color but not the entire row because another .css file rule is governing this one already or 2 are conflicting. conflict resolution on this one.

try to remove the element into a new file/folder and see if it runs sepereate. if it does you know you have a conflict in css rules.

Happy hunting!

In my case, my password was reset. When connecting, I changed the Authentication to another option then back to "SQL Server Authentication". After it, when I hit "Connect" it asked me to update the password.

had the same problem time ago, i solved by updating the library. If not work after updating try pymysql instead of mysql.

I tried to use the merchant ID under "Business Information" and it was wrong, mine was in the url bar and was 13 characters, the wrong one for me was ALL numbers and only 12 numbers.

1 moveTo(x, y) {

2 this.nodes[0].updateRelative (true, true);

3 let dist ((x this.end.x) **2 +

4 (y this.end.y) **2) ** 0.5;

5 let len = Math.max(0, dist this.speed);

6 for (let i= this.nodes.length 1; i >= 0; i--) {

7 let node = this.nodes[i];

8 let ang Math.atan2(node.yy, node.x x);

9 node.x = x + len * Math.cos(ang);

10 node.y = y + len Math.sin(ang);

11 x = node.x; y = node.y; len = node.size;

12}

13 update() {this.moveTo(Input.mouse.x, Input.mouse.y)}

document.getElementById("Button").disabled = true;

I used prebuilt aar,
If it is not available you can follow this

https://medium.com/@213maheta/ffmpeg-create-aar-file-add-it-into-android-project-7e069b0fe23f

i) Run below command on terminal

git clone https://github.com/arthenica/ffmpeg-kit.git
or Download source code from below link

https://github.com/arthenica/ffmpeg-kit

ii) Open termial & give path for Android SDK & NDK

export ANDROID_SDK_ROOT=/..your_path../Android/Sdk
export ANDROID_NDK_ROOT=/..your_path../Android/Sdk/ndk/25.1.8937393
iii) Run below command

./android.sh
iv) Go to dir

…./ffmpeg-kit/prebuilt/bundle-android-aar/
v) Copy ffmpeg-kit.aar & put it in to below path

project_name/app/libs/
vi) Add below line in your app gradle

dependencies {
    implementation(files("libs/ffmpeg-kit.aar"))
}

I was able to make a patch at GenerateNode in PropertyCodeGenerator:

result.Type = type;

//Add this code
if (element.GenericReturnTypeIsNullable())
{
    var simpleType = type as RtSimpleTypeName;
    var genericArguments = simpleType.GenericArguments.Cast<RtSimpleTypeName>().ToArray();
    for (int i = 0; i < genericArguments.Length; i++)
    {
        var genericArgument = genericArguments[i];
        genericArguments[i] = new RtSimpleTypeName(genericArgument.TypeName + " | undefined");                    
    }
    result.Type = new RtSimpleTypeName(simpleType.TypeName, genericArguments);
}

This proves what I want to achieve is possible but unfortunately means I will have to make my own version of the library to accommodate this change.

Keep in mind the solution above is not 100% complete as it doesn't check the index of each generic argument, it only assumes if one is nullable then all are :) I leave this as an exercise for the readers...

If there is a better way please let me know so I am not reinventing the wheel.

Thank you!

Same error, found this issue https://github.com/vercel/next.js/issues/81751 and decided to update next to newest 15.4.5 and it seems to work now

Depending on the reason, you will likely need to access local business directories, map APIs, or utilize data scraping tools to acquire business listings with geocodes (latitude and longitude) for a given area.

1. Use Google Maps API or Bing Places API

With business Google Map and Bing Places APIs, you can search for and retrieve classified businesses within a particular area, and they will return the results indicating business titles, locations, addresses, and geocodes. Of course, a developer key is a prerequisite.

2. Third-party Data Providers

Other websites, for instance, Data Axle or Yelp, Foursquare API, do provide their business datasets with geocodes but usually for a price.

3. Scraping Local Directories with Permission

Some public directories, for example, EZ Local, show businesses with their city and state but do not provide geocodes. However, if the business or geocoding address is offered, you can apply geocoding APIs for translating the address to latitude and longitude, such as Google’s.

Note:

Always check the conditions of service of sites such as EZ Local concerning their data policies before scraping or programmatically extracting data.

نیوشا علیپور است شماره ش را بده

It looks that the source originates from an example I wrote for a STM32World Tutorial video. IF you have not watched the video, I'd recommend that as it goes through the setup in STM32CubeMX. I don't see anything obviously wrong in your code, so most likely it is in the CubeMX setup.

https://www.youtube.com/watch?v=0N4ECamZw2k

The working example for STM32F405 is here: https://github.com/STM32World/stm32fun/tree/master/stm32world_dac1

Instead of commenting out lines or manually editing expressions, you can filter elements directly in a vector:

x = [1,2,3,4,5];
total = sum(x(~ismember(x, [2 4])));  % Exclude 2 and 4 from the sum

I have finally find a solution for the given issue. I will recommend you to use powershell with Az module to process the commands. Make sure you have installed the Az module in your powershell in order to perform the bash commands.

1. First identify the app id for your registered application in the azure.

2. Once you have the app id for me i faced an error where i was not able to read or access the certificate from Azure key vault because of error - "Caller is not authorized to perform action on resource.\r\nIf role assignments, deny assignments or role definitions were changed recently, please observe propagation time.

3. To properly access the Key vault i would recommend to provide role based access on the app id for Key Vault Administrator and Key Vault Certificates Officer.

4. Over here as your application is trying to access the key vault from your custom program you will have to provide role based access on the Service Principal. For more information please refer to -

https://learn.microsoft.com/en-us/azure/databricks/admin/users-groups/service-principals

5. So consider your app needs an active Service principal and provide the access of required role to the given service principal.

6. Commands to see and apply the role for your service principal is as follows-

   1. Verify if a service principal exists for the application:
      bash

   • az ad sp show --id [app-id]**

     If it fails with Service Principal not found then create it with

     az ad sp create --id [app-id]

   2. Once you have an active sp in your tenant then next step is to assign the role

      az role assignment create --assignee app-id/client-id --role "Key Vault Certificates Officer" --scope /subscriptions/[subscription-id]/resourcegroups/[resourcegroupname]/providers/Microsoft.KeyVault/vaults/[vault-name]

   3. az role assignment create --assignee app-id/client-id --role "Key Vault Administrator" --scope /subscriptions/[subscription-id]/resourcegroups/[resourcegroupname]/providers/Microsoft.KeyVault/vaults/[vault-name]

   4. If you have system managed identity enabled by default for Virtual Machine on azure then also add that app-id similarly with the command.

7. Once you do this please wait 15-20 minutes approximately for the assignment of roles properly and test like sending emails after this, I did this for setting up certification based authentication for our Oauth2 setup.

Have you found a solution for this?

Click the View Menu button and then select Show->Errors/Warnings on Project.

running with:

docker compose up -d

instead of:

docker-compose up -d

If you were able to give each combination an item ID (outside of PBI desktop), and then use the sort column based on that specific ID, this would work.

For example,

You would then create the order column based on ID and "Sort by Column" with this the order.

If you only sorted on the "sizing" classification, all Kings will be grouped together, all Queens will be grouped together, etc. (which I'm sure you've already seen).

Another way to accomplish this (depending how you want to do it) would be a custom column using DAX that would look something like this:
(For just itemorder)
OrderColumn = IF(table[Item] = "Bed", 1
IF(table[Item] = "Box Spring", 2
...................)

OR

(For item AND size order)
OrderColumn = IF(AND(table[Item] = "Bed", table[Sizing] = "King"), 1
IF(AND(table[Item] = "Bed", table[Sizing] = "Queen"), 2
...................)

Generate a realistic, high-resolution image that visually represents the following scene or concept in a natural, photorealistic style. The image should look like it belongs in a premium blog post—minimal, clear, and emotionally resonant—without any text, labels, or graphics. Scene to Visualize:[paste your text here] Visual Style & Composition:Use natural or ambient lighting that fits the tone of the scene (e.g., warm for cozy/home scenes, cool for modern/tech topics, bright for energetic content).Prioritize realism and believability—include depth, shadows, reflections, textures, and natural imperfections where appropriate.Background should either enhance the scene (if contextual) or be minimal/blurred to keep focus on the main elements.Use camera-like perspectives (eye-level, overhead, or close-up) depending on what best suits the scene.Avoid clutter. The image should feel clean and visually balanced, with a clear subject or focal point. Color & Tone:Stick to modern color palettes trending in blogs and digital publications: soft neutrals, warm tones, elegant muted hues, natural greens/blues, or high-contrast blacks and whites.Optional: add a subtle filter or lighting grade that gives the image a cinematic or editorial blog-style finish. Do NOT Include:No text or overlays of any kindNo branding, logos, watermarksNo cartoonish or unrealistic renderingsThe final result should feel like a high-end editorial photo or a lifestyle stock image used by top-tier blogs (like Medium, Substack, Notion templates, or branded blogs by Apple, Airbnb, etc.).

Python 3.13.2 (main, Feb  4 2025, 00:00:00) [GCC 14.2.1 20250110 (Red Hat 14.2.1-7)] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import os
>>> import tempfile
>>> tempfile.gettempdir()
'/tmp'
>>> os.environ["TMP"] = "/tmp/xis"
>>> tempfile.gettempdir()
'/tmp'

There are perspectives to consider here.

Among the classes that implement the interface, there is greater coupling, but not as strong. This coupling is even stronger in versions prior to Java 8, in which classes that implement these features MUST be recompiled if any new functionality is added to the interface. Although classes must implement the functionality themselves, there is no dependency on the implementation of the functionality, just a set of functionalities to be implemented.

For those who use it, reusing the interface's functionalities through polymorphism is very good coupling and requires no modification.

And from the interface's perspective, there is a larger set of possible classes that can use the interface.

Did you end up having to combine your certs into one .pfx file and then using that in your .csdef file? e.g.

    <Certificates>
      <Certificate name="cert-fullchain" thumbprint="B50C067CEE2B0C3DF855AB2D92F4FE39D4E70F1E" thumbprintAlgorithm="sha1" />
    </Certificates>

set :

logging: console.log()

This way you will have all the queries logged on to the console, irrespective of what kind of query it is.

Place your properties in a location that loads before auto-configuration:

@SpringBootApplication
@PropertySource("classpath:/WEB-INF/my-web.properties")
public class MyApplication {
    public static void main(String[] args) {
        SpringApplication.run(MyApplication.class, args);
    }
}

ol {
  overflow-x: auto;
  padding: 0;
  margin: 0;
  white-space: nowrap;
}

li {
  display: block;
  white-space: pre;
  min-width: 100%;
}

Jimi's post helped a lot. I used the post to create a class that derives from Form like below and now scrolling works fine. Thank you Jimi!

[DesignerCategory("code")]
public class Myform:Form,IMessageFilter
{
   
   
        public Myform()
        {
          //  SetStyle(ControlStyles.UserMouse | ControlStyles.Selectable, true);
          this.AutoScroll = true;
          
        }

        protected override void OnHandleCreated(EventArgs e)
        {
            base.OnHandleCreated(e);
            Application.AddMessageFilter(this);

            VerticalScroll.LargeChange = 60;
            VerticalScroll.SmallChange = 20;
            HorizontalScroll.LargeChange = 60;
            HorizontalScroll.SmallChange = 20;
        }

        protected override void OnHandleDestroyed(EventArgs e)
        {
            Application.RemoveMessageFilter(this);
            base.OnHandleDestroyed(e);
        }

        protected override void WndProc(ref Message m)
        {
            base.WndProc(ref m);
            switch (m.Msg)
            {
                case WM_PAINT:
                case WM_ERASEBKGND:
                case WM_NCCALCSIZE:
                    if (DesignMode || !AutoScroll) break;
                    ShowScrollBar(this.Handle, SB_SHOW_BOTH, true); //was false
                    break;
                case WM_MOUSEWHEEL:
                    // Handle Mouse Wheel for other specific cases
                    int delta = (int)(m.WParam.ToInt64() >> 16);
                    int direction = Math.Sign(delta);
                    ShowScrollBar(this.Handle, SB_SHOW_BOTH, true); //was false
                break;
            }
        }

        public bool PreFilterMessage(ref Message m)
        {
            switch (m.Msg)
            {
                case WM_MOUSEWHEEL:
                case WM_MOUSEHWHEEL:
                    if (DesignMode || !AutoScroll) return false;
                    if (VerticalScroll.Maximum <= ClientSize.Height) return false;
                    // Should also check whether the ForegroundWindow matches the parent Form.
                    if (RectangleToScreen(ClientRectangle).Contains(MousePosition))
                    {
                        SendMessage(this.Handle, WM_MOUSEWHEEL, m.WParam, m.LParam);
                        return true;
                    }
                    break;
                case WM_LBUTTONDOWN:
                    // Pre-handle Left Mouse clicks for all child Controls
                    if (RectangleToScreen(ClientRectangle).Contains(MousePosition))
                    {
                        var mousePos = MousePosition;
                        // Inside our bounds but it's not our window
                        if (GetForegroundWindow() != TopLevelControl.Handle) return false;
                        // The hosted Control that contains the mouse pointer 
                        var ctrl = FromHandle(ChildWindowFromPoint(this.Handle, PointToClient(mousePos)));
                        // A child Control of the hosted Control that will be clicked 
                        // If no child Controls at that position the Parent's handle
                        var child = FromHandle(WindowFromPoint(mousePos));
                    }
                    return true;
                    // Eventually, if you don't want the message to reach the child  Control
                    // return true; 
            }
            return false;
        }

        private const int WM_PAINT = 0x000F;
        private const int WM_ERASEBKGND = 0x0014;
        private const int WM_NCCALCSIZE = 0x0083;
        private const int WM_LBUTTONDOWN = 0x0201;
        private const int WM_MOUSEWHEEL = 0x020A;
        private const int WM_MOUSEHWHEEL = 0x020E;
        private const int SB_SHOW_VERT = 0x1;
        private const int SB_SHOW_BOTH = 0x3;

        [DllImport("user32.dll", SetLastError = true)]
        private static extern bool ShowScrollBar(IntPtr hWnd, int wBar, bool bShow);

        [DllImport("user32.dll", CharSet = CharSet.Unicode, SetLastError = true)]
        private static extern int SendMessage(IntPtr hWnd, uint uMsg, IntPtr wParam, IntPtr lParam);

        [DllImport("user32.dll")]
        internal static extern IntPtr GetForegroundWindow();

        [DllImport("user32.dll")]
        internal static extern IntPtr WindowFromPoint(Point point);

        [DllImport("user32.dll")]
        internal static extern IntPtr ChildWindowFromPoint(IntPtr hWndParent, Point point);
    }

as long as DtoService.GetDtos() it is being used,using var context = new dtoContext(...) itcontext gets properly disposed of even though you're creating DtoService without DI. It's short-lived and doesn't hold resources, so there's no memory leak risk and no need to manually dispose of anything. MyService since you're not holding the EF context there, your provider pattern with DataService is a good way to avoid cluttering DI with multiple DB context services make sure you don’t accidentally hold onto instances of DtoService or the context longer than needed

C is like Python, if you have 9 slots for an array, you will have 0 to 8 as indices. C is very serious about memory as it is a low-level language. You would have to allocate print vettore [8] if you are trying to access the last element.

For me it turned out to be necessary to manually copy the precompiled libraries from CefGlue/packages/cef.redist.linux64/120.1.8/CEF/ (from sources) to bin folder.

os.system("helpfile.pdf") goes to next line when file is open. It doesn't wait until user close it. So helpfile_btn is deactive only for a moment because the next line makes it working again. I don't think that it's possible to do with reader that select in system. In windows you can't get access to reader. And almost you don't know to witch. Acrobate? Chrome? Firefox... Maby don't do it or make reader a part of your программе?

I would suggest using QLoRA for fine tuning and try using a well defined format for the fine tuning data like :
{messages: [{"role" :"system", "content" : "......"}, {"role": "user", "content" : "...."}, {"role" : "response", "content" : "......"}]

Also try using a suitable optimizer during fine tuning like adamw

I could provide more detailed solution if you can share your fine tuning approach.

Successfully opened terminal window and executed commands using this code

# Open an xterminal in colab

!pip install colab-xterm

%load_ext colabxterm

%xterm

#Then ran following commands in window

curl -fsSL https://ollama.com/install.sh | sh

ollama serve & ollama pull llama3 & oll

You can check any conditions you want in the Exit block - like

if (TargetVessel==2) {
    PrepareLoading.take(agent);
}

However what happens to the agents that cannot be taken? You'd need some sort of control logic - most likely, you should only take from storage the agents that CAN be sent to the exit block. Thus, you are ensuring all agents that are finished storing.

Based on both answers above, this is the minimum code I could get it to work on .NET 8.

//1. Add SwaggerUI
app.UseSwaggerUI(c =>
{
  c.RoutePrefix = "api/something/else/swagger";
});

//2. Set BasePath
app.UsePathBase("/api/something/else");

//3. Add Swagger
app.UseSwagger();

start your spring boot project from here:

https://start.spring.io/

get project.zip

unzip the project.zip

you can find: pom.xml

「

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <parent>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-parent</artifactId>
        <version>3.5.4</version>
        <relativePath/>
    </parent>
    <groupId>com.emea</groupId>
    <artifactId>project</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <name>project</name>
    <description>Demo project for Spring Boot</description>
    <properties>
        <java.version>21</java.version>
    </properties>
    <dependencies>
        <dependency>            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>

        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <optional>true</optional>
        </dependency>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <annotationProcessorPaths>
                        <path>
                            <groupId>org.projectlombok</groupId>
                            <artifactId>lombok</artifactId>
                        </path>
                    </annotationProcessorPaths>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-maven-plugin</artifactId>
                <configuration>
                    <excludes>
                        <exclude>
                            <groupId>org.projectlombok</groupId>
                            <artifactId>lombok</artifactId>
                        </exclude>
                    </excludes>
                </configuration>
            </plugin>
        </plugins>
    </build>

</project>

(1) Use the spring-boot-maven-plugin to build the Spring Boot application JAR. Do not use the maven-jar-plugin.

(2) In the section of your pom.xml, do not manually specify the versions of dependencies that are already managed by Spring Boot (e.g., 3.5.3, 1.18.38, 6.2.9).

(3) You can use the mvn dependency:tree command to identify the libraries and versions that are already included by Spring Boot.

package and run:

package

mvn clean package

run

java -jar target/project-0.0.1-SNAPSHOT.jar

then everything is ok!

2025-08-06T23:52:06.643+08:00  INFO 17710 --- [project] [           main] com.emea.project.ProjectApplication      : Started ProjectApplication in 1.387 seconds (process running for 1.986)

To reproduce your issue, simply modify the pom.xml as follows:

add

<plugin>
    <groupId>org.apache.maven.plugins</groupId>
    <artifactId>maven-jar-plugin</artifactId>
    <version>3.3.0</version>
    <configuration>
        <archive>
            <manifest>
                <mainClass>${exec.mainClass}</mainClass>
            </manifest>
        </archive>
    </configuration>
</plugin>

remove

<plugin>
    <groupId>org.springframework.boot</groupId>
    <artifactId>spring-boot-maven-plugin</artifactId>
    <configuration>
        <excludes>
            <exclude>
                <groupId>org.projectlombok</groupId>
                <artifactId>lombok</artifactId>
            </exclude>
        </excludes>
    </configuration>
</plugin>

add

<exec.mainClass>com.emea.project.ProjectApplication</exec.mainClass>

into <properties>

modify ProjectApplication.java like yours.

package and run:

package

mvn clean package

run

java -jar target/project-0.0.1-SNAPSHOT.jar

then get the same error:

$ java -jar target/project-0.0.1-SNAPSHOT.jar
Exception in thread "main" java.lang.NoClassDefFoundError: org/slf4j/LoggerFactory
    at com.emea.project.ProjectApplication.<clinit>(ProjectApplication.java:11)
Caused by: java.lang.ClassNotFoundException: org.slf4j.LoggerFactory
    at java.base/jdk.internal.loader.BuiltinClassLoader.loadClass(BuiltinClassLoader.java:641)
    at java.base/jdk.internal.loader.ClassLoaders$AppClassLoader.loadClass(ClassLoaders.java:188)
    at java.base/java.lang.ClassLoader.loadClass(ClassLoader.java:526)
    ... 1 more

how to fix ?

• remove maven-jar-plugin
• add spring-boot-maven-plugin

On my end, I don't find the conversion to datetime mentioned by @piRSquared to be necessary. You can just do:

df[<column_name>] = df[<column_name>].astype(str)
df.to_dict('records')

Solution is to Check your Python version

MediaPipe only supports:

Python 3.7 to 3.11

i was trying with the 3.11.9 version of python then it installed successufuly

Unsafe.AreSame is the less-unsafe equivalent of pointer equality.

I have no IT background , but what i understood so far , a daemon is a background process that is continuously running to do certain tasks for client, but APIs are communication programs between programs or application.

If you're using Unity Catalog, you can now query columns easily with:

SELECT table_schema, table_name, ordinal_position, column_name, data_type, full_data_type
FROM main.information_schema.columns
ORDER BY 1,2,3;

Where main is the name of your catalog. You can read more about it here.

The reason is this class that changes the behaviour of Android classes manipulating the bytecode

https://cs.android.com/android-studio/platform/tools/base/+/mirror-goog-studio-main:build-system/builder/src/main/java/com/android/builder/testing/MockableJarGenerator.java;l=60?q=MockableJarGenerator&ss=android-studio/platform/tools/base

For me, adding "read_private_products" capability in WooCommerce v10.0.4 allowed a customer user to be able to read the products endpoint in v3 (/wp-json/wc/v3/products)

just pass --js=true flag in your command

Adding the following line to my config fixes it!

"editor.suggest.showReferences": false

with function row_count(tab_name in varchar2) return number as
    rc number;
begin
    execute immediate 'select count(*) from ' || tab_name into rc;
    return rc;
end;
select table_name, row_count(table_name) as row_count from all_tables
    where owner = 'owner';
/

I see annotations on all panels in Grafana v11.3.1 (64b556c137) with Grafana as datasource for Annotation Queries with these steps

1. create a manual annotation (point or range)
   1.1 click on a point in dashboard - not on time but there has to be a tooltip open
   1.2 select a range -> press CMD/Option (mac) before releasing -> create a range annotation

2. Go to settings -> Annotations -> create a new annotation in Grafana -> leave Grafana as a source -> don't change anything

3. Return to your Dashboard -> you see your initial manual annotation copied to all panels

Try this Check Blog

        if(Auth::guard('web')->check()){
            $user = Auth::guard('web')->user();
        }

I get this behavior when calling in using PSTN, however if you call directly through teams using the UPN of the resource account it should work. Probably a bug on Microsoft's side.

Try the SavePicture command.

Private Sub SaveActiveXImage()
    
    Dim filePath As String
    filePath = "your\filepath.jpg"
    
    SavePicture Picture:=Sheets("Sheet1").Image1.Picture, Filename:=filePath

End Sub

Full disclosure, this came from this forum post.

But Embarcadero's website clearly states that FastReport Embarcadero Edition is already included in Delphi 12 CE. So there should be no need for us to do anything but click Fastreport components in the tool palette.

I have found I needed to do the following:

If there isn't enough data to flesh out the requested number of frame bytes to return, return the truncated number of bytes extended with empty (0x00) bytes to equal the frame size. This extended data is returned with paContinue. This should keep the stream from being closed prematurely.

However, my code knows when no more output is expected, so I close the stream at that point. When new output is available, I check if the stream is inactive and attempt to start it. If this fails, I stop, close, and reopen the stream.

i have found my problem, when xcodebuild is run with signing, he rebuild the Runner binary, but without he don't, so i need to select my xcode version before xcodebuil run

I had the exact same issue on my new 5070ti, was able to fix it by upgrading PyTorch to CUDA 12.8. For anyone who needs it, what I ran was:

pip install -U torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128

In quarto, the following works for me:

[Download the data](data.csv){download=""}

I have found what was missing.

Queued notification will not work if the notifiable model is not persisted. This is not an issue when ShouldQueue is not implemented.

I ended up using

https://github.com/fivecar/react-native-draglist

This really saved me, and I now totally removed draggable flatlist from my project.

You can do it using EnumFeature.WRITE_ENUMS_TO_LOWERCASE since version 2.15.

Full example of ObjectMapper creation:

public static ObjectMapper createObjectMapper() {
    ObjectMapper objectMapper = new ObjectMapper();
    objectMapper.configure(EnumFeature.WRITE_ENUMS_TO_LOWERCASE, true);
    return objectMapper;
}

You can do it using EnumFeature.WRITE_ENUMS_TO_LOWERCASE since version 2.15.

Full example of ObjectMapper creation:

public static ObjectMapper createObjectMapper() {
    ObjectMapper objectMapper = new ObjectMapper();
    objectMapper.configure(EnumFeature.WRITE_ENUMS_TO_LOWERCASE, true);
    return objectMapper;
}

<style>
  * {
    list-style-type: none;
    margin: 0;
    padding: 0;
  }

  div, li {
    border: 1px solid rgb(142, 28, 47);
  }

  .header {
    display: grid;
    grid-template-columns: 5fr 1fr 1fr;
  }

  ul {
    display: flex;
    justify-content: space-between;
    margin-top: 10px;
  }
</style>

<div class="header">
  <div class="Search">Search</div>
  <div class="Alert">Alert</div>
  <div class="User Info">User Info</div>
  <div class="Intro">Hi There</div>
  <ul>
    <li>New</li>
    <li>Upload</li>
    <li>Share</li>
  </ul>
</div>
justify-items controls how items are aligned inside each individual grid cell, not how the items themselves are spaced in the container.
space-between is not a valid value for justify-items.

You can just import keras instead of import tensorflow.keras (In my case, Tensorflow version 2.10.1 and Python 3.10.11 and keras version 2.10.0)

Example usage in vscode

I ran into such SSL-related issue with an old RabbitMQ.Client (version 3.5.7.0). Upgrading to a newer client (in my case 6.5.0.0 as I need to target .NET Framework 4.6.1) solved the issue without any code changes). The code was not specifying full Uri, but rather setting individual properties: HostName, Port, UserName, Password, VirtualHost.

Recheck kafka-offset topics. If you use AWS MSK, try to call the system topics differently.

You're building a FinTech app and using RootBeer for root detection, but it fails with Magisk + Zygisk + DenyList enabled, which hides root.

You're asking:

1. How to detect root even with advanced hiding (Zygisk, DenyList)?

2. What extra tools or methods can help bypass this obfuscation?

3. How to block the app from running on such devices?

You're looking for stronger root detection to protect your app from tampered environments.

import numpy as np

def cofactor(A,r,c):
    nr, nc = A.shape
    B = np.zeros((nr-1,nc-1))
    for i in range(nr-1):
        for j in range(nc-1):
            s, t = i, j
            if i>=r:
                s = i+1
            if j>=c:
                t = j+1
            B[i,j] = A[s,t]
    return B

def rcdet(A):
    nr, nc = A.shape
    if nr == 1:
        return A[0,0]
    else:
        t = 0.0
        for j in range(nc):
            t += ((-1)**j)*A[0,j]*rcdet(cofactor(A,0,j))
        return t

I love Nextjs and I love Django, setting them up together takes the fun out of being dev. So, although I do think it is good to know how to set them up manually for experience, you should try nextjango.

nextjango.org

or just type “npx nextjango init” into the CLI and it does everything for you, as long as you have a package manager (npm pnpm yarn bun) and have Python installed on your machine, after running the command you only have to enter npm run dev (or your-package-manager run dev) and it starts both servers and does a server health check and displays the status on the Nextjs frontend homepage. It’s fast, and easy. Not much documentation yet as it’s very new, but it does work good and has extensive unit testing that has been done to ensure the integrity, you can check it out the GitHub too

where you able to solve this? I have the same issue

I have the same problem, but my case is worst.

The org has more than thousands repositories and include all repos into the credential is not an option.
I would love to know if there is other way to solve this.

I figured it out! Had to check Yes in the Tax Schedule for North Carolina.

React state updates are asynchronous, so UI changes might not appear instantly if you're not reflecting the state visually. To show the active (clicked) button right away, use a separate state (like clickedOption) and conditionally apply a CSS class to highlight the selected button.

From my testing, it looks like PDAL isn't currently supported by Ubuntu 24.04. The only way I was able to get PDAL working was to revert to 22.04. Not sure if this will transfer over to QGIS, but I suspect that it will since QGIS is simply calling PDAL functions.

This might be helpful for you auto-type-code, it has many great options

Answer based on the comment of @jon-spring and ggplot2 documentation:

You can duplicate the x-axis by defining a secondary x-axis in the scale_x_* call. For example: scale_x_continuous(sec.axis = dup_axis())

The breaks, labels, and title of the duplicated axis can be formatted via dup_axis() arguments.

Using the iris dataset:

library(ggplot2)
ggplot(iris, aes(Sepal.Length, Sepal.Width)) +
    geom_point() +
    scale_x_continuous(sec.axis = dup_axis(name="example title", breaks=c(5, 5.5, 6)))

The same procedure is possible also for y-axis.

Try this. It works. Clearly described all steps to reproduce.

https://medium.com/@dmitry.ivanov.iamm/auth-an-expo-react-native-ios-app-with-nextauth-702c2c71004f

It can be appropriate (example described here where the goal is to make more urgent parts of the page render earlier), but probably not in the situation you describe. As another answer hints, you don't seem to provide valid arguments for doing that in your situation.

It simply does not work, the tool doesn’t even bother storing remaining work for completed cards and their date of completion, as @Roland pointed out, even Microsoft’s own documentation shows 0% completion in their screenshots. And yes, this was reported on MS forums — their response? 'Not a bug.' Apparently, you're just supposed to switch to 'Count of Work Items' because otherwise, it’ll always sit at 0%. My hate for Microsoft grows stronger every day.

In angular 20 try to set --mat-progress-bar-active-indicator-color to set value.

--mat-progress-bar-active-indicator-color : red!important;

If anyone thinking how I get that I just changed its calculated css in browser and backtrack then get which file defines that and get this variable.

Worked for me. Remove Min SDK version on all modules.

Try like this.

$builder->when(! $builder->getQuery()->unions
               && is_null($builder->getQuery()->aggregate),
    function ($query) {
        $query->orderBy('priority');
    }
);

Struggling with the same issue ( i am logged in - no captcha ) when visiting a user profile page - captcha before feed gets loaded. This doesnt happen local only on my virtual machine setup (where the browser runs headless) . Even with installing a virtual display on the vm to run non headless same issue. Did you manage to find a solution ? I am using Nodriver (follow-up of UC ) .. kind regards

Check out Mp3tag. It's a cool little tool that lets you edit stuff like the title, artist, album, year, cover, etc. It's only about 16 MB and it's totally free for Windows.

Plus, you can update tags for all the files in a folder with just one click. Super handy!

Microsoft Store (Free) - https://apps.microsoft.com/detail/9nn77tcq1nc8
AppStore (25$) - https://apps.apple.com/us/app/mp3tag/id1532597159?mt=12

The official webpage - https://www.mp3tag.de/en/

Mp3tag preview picture - https://i.sstatic.net/3KrEPjTl.png

try using reportLevelFilters list in below format instead of basic filter format.

{
  "format": "PDF",
  "powerBIReportConfiguration": {
    "reportLevelFilters": [
      {
        "filter": "TableName/FieldName eq 'Value'"
      }
    ]
  }
}

Turns out the implementation of my code in the OP is correct. The issue, as pointed out by @feras in the comments, was with curl, which uses a buffer. By default, the data is only returned when the buffer is full, or a newline character is encountered. Setting `--no-buffer` solved the issue.

There is no way to do that. With ExpressionsBasedModel you do not model constant parts of any expression (constraint or objective).

The text of this answer was originally written by khmarbaise in a comment.

Here is the issue .

Tldr, LineageOS builds its ROM as userdebug. However, Android Studio assumes that devices with non-user build type have su executable when using APP Inspector and Layout Inspector.

So I make a simple Magisk module to workaround it. Use at your own risk.

You can directly apply the html header tags is blazor component like "<h1>hello, buddy</h1>".

I hope it will help you.

Acknowledging the warnings in the other answer, if you have git and want to apply a template over the top of an existing project, simply run cookiecutter with the -f flag. Make sure the output directory matches your target directory. Once that's done, run a git diff and decide what you want to keep.

Building from commandline, add -ubtargs"-MyArgument"
In Target.cs, read them like so, for example :

[CommandLine(Prefix = "-MyArgument")] 
public bool MyArgument = false;

and then make it a definition like this:

ProjectDefinitions.Add(MyArgument ? "MYARG=1" : "MYARG=0");