messages
listlengths 3
3
|
|---|
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-config - Get and set repository or global options status.branch"
},
{
"role": "assistant",
"content": "Set to true to enable --branch by default in git-status .\nThe option --no-branch takes precedence over this variable."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Recover a deleted repository github issues\n\nMy repository in the github had been deleted.\nThe code was recovered, but we had a lot of Github issues i'd like to recover, is there a way to recover them once deleted?\nThanks."
},
{
"role": "assistant",
"content": "You need to email [email protected] as soon as possible when this happens."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Git for Windows - The Program can't start because libiconv2.dll is missing\nWhen I attempt to run certain commands (like git push, for example) from a git Bash on Windows 7 (64bit) I get the error:\nThe program can't start because libiconv2.dll is missing from your computer\n\nI have searched exhaustively for a solution to this.\nThe most I can find is an issue thread at the google code site (Issue 419) and a few other blogs here and there. As far as I can tell none of the suggestions offered in the posts will actually solve my issue.\nI have tried re-installing. I have tried adding $GIT/bin to the PATH.\nI can verify that the dll is in the $GIT/bin directory...but still I cannot push to remote.\nI have a working install of msysgit on another Windows 7 box, and I installed the same way in both situations... so needless to say I am quite confused.\nAny help on this would be most appreciated.\nThanks,"
},
{
"role": "assistant",
"content": "Work around from this thread: http://groups.google.com/forum/#!topic/msysgit/twrVn_EbNI4 \n\ncd into your git install directory\ncopy mingw\\bin\\libiconv-2.dll libexec\\git-core\n(or copy bin\\libiconv-2.dll libexec\\git-core if your installation has no mingw folder)\n\nIn the linked thread Drew asks for assistance, so if you think you can help fix it you might want to reply in that Google Groups thread.\nError happens with these builds:\n\nmsysgit-fullinstall-1.7.4 OR 1.7.6 (and 1.7.7)\nmsysgit-netinstall-1.7.4 OR 1.7.6 (and 1.7.7)\nGit For Windows 1.7.6 (but not 1.7.4)"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Visual Studio 2017 Enterprise + TFS 2018 + Git Clone = Unable to get local issuer certificate\nI'm new to interact with Git and I'm trying to combine it with TFS infrastructure, but experiencing SSL authentication problems. No Github, no VSTS. TFS is on-premises, therefore local installation.\nServer part:\nI've installed TFS 2018 on Windows Server 2016 and create a corporate self signed certificate and bind the TFS web service (IIS manager) on that certificate.\nTFS is configured to run only through HTTPS. HTTP is redirected to HTTPS.\nI've setup a new Project with Git as versioning system.\nClient part:\nI have two kind of Windows clients. Windows 7 SP1 and 10 Anniversary Update, both of them with Visual Studio 2017 Enterprise.\nI installed the certificate (as Trusted Root Certification Authorities) and connecting through browser I have no whatsoever to see the project informations. \nNo browser raise any kind of alerts regarding authenticity of certicate.\nThen, I installed Git-2.15.1.2-64-bit.exe, using Windows Secure Channel Library.\nI followed this guide to configure Git clients, because I was getting title fatal error.\nSo basically I extracted content of self-signed and appended to ca-bundle.crt file. \nAll of them:\n\nC:/Program Files/Git/mingw64/ssl/certs/\nC:\\users\\myname (created as a global one just like guide says)\nC:\\Program Files (x86)\\Microsoft Visual Studio\\2017\\Enterprise\\Common7\\IDE\\CommonExtensions\\Microsoft\\TeamFoundation\\Team Explorer\\Git\\mingw32\\ssl\\certs (this is created by Visual Studio 2017 installation)\n\nWhen I use through Powershell \"git config --list --show-origin\" command, I see listed:\nfile:\"C:\\Program Files\\Git\\mingw64/etc/gifconfig\" http.sslcainfo=C:/Program Files/Git/mingw64/ssl/certs/ca-bundle.crt\nfile:\"C:/users/myname/.gifconfig\" http.sslcainfo=C:/users/myname/ca-bundle.crt\nIf I try to clone repository from VS2017 Team Explorer panel it keeps saying:\n\"Git failed with a fatal error.\nfatal: unable to access 'https://tfs.blahblah/': SSL certificate problem: unable to get local issuer certificate\"\nBut when I use Git GUI it answers with a different error: \nfatal: Couldn't find remote ref HEAD\nAs far as I know it looks reasonable because there is no commit attached.\nBut I can't commit anything if I can't \"pair\" with Visual Studio 2017.\nI read through several links, but I couldn't get it through. So before mark it as duplicated, I ask you to PLEASE pay attention to my specific system/environment requirements.\nNote: and please don't suggest me to switch off SSL because as already talked it is NOT a solution in corporate/enterprise environments"
},
{
"role": "assistant",
"content": "Here what I did to fix my issue:\nIn Git Settings, Global Settings in Team Explorer, there is an option to choose between OpenSSL and Secure Channel.\nStarting with Visual Studio 2017 (version 15.7 preview 3) use of SChannel in Git Global settings fixed my issue."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-format-patch - Prepare patches for e-mail submission -q --quiet"
},
{
"role": "assistant",
"content": "Do not print the names of the generated files to standard output."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Gitlab CI: Cannot find output of build stage\n\nI have my .gitlab-ci.yml file set up in the typical three stages: test, build, deploy. During the build stage, I run a command that compiles my project and puts it in a tarball. The build stage appears to execute successfully because it moves on to the deploy stage, but the deploy stage then says it can't find the tarball. Is it in another directory? What happened to it? Thanks."
},
{
"role": "assistant",
"content": "For each test gitlab-ci clean the build folder, therefore the output files of the build stage are not available in the deploy stage.\nYou need to rebuild your project also in the deploy stage.\nThe \"stages\" are only useful to order your tests, i.e. avoid to try to do a deploy test if a build test failed.\nEDIT:\nSince Gitlab 8.6, it is possible using dependencies feature"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-remote - Manage set of tracked repositories add"
},
{
"role": "assistant",
"content": "Add a remote named <name> for the repository at\n<URL>. The command git fetch <name> can then be used to create and\nupdate remote-tracking branches <name>/<branch>. With -f option, git fetch <name> is run immediately after\nthe remote information is set up. With --tags option, git fetch <name> imports every tag from the\nremote repository. With --no-tags option, git fetch <name> does not import tags from\nthe remote repository. By default, only tags on fetched branches are imported\n(see git-fetch ). With -t <branch> option, instead of the default glob\nrefspec for the remote to track all branches under\nthe refs/remotes/<name>/ namespace, a refspec to track only <branch> is created. You can give more than one -t <branch> to track\nmultiple branches without grabbing all branches. With -m <master> option, a symbolic-ref refs/remotes/<name>/HEAD is set\nup to point at remote’s <master> branch. See also the set-head command. When a fetch mirror is created with --mirror=fetch , the refs will not\nbe stored in the refs/remotes/ namespace, but rather everything in refs/ on the remote will be directly mirrored into refs/ in the\nlocal repository. This option only makes sense in bare repositories,\nbecause a fetch would overwrite any local commits. When a push mirror is created with --mirror=push , then git push will always behave as if --mirror was passed."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "fatal: in unpopulated submodule\n\nI am quite new to github and I am trying to find a solution to a current problem that I am having. I will go through my process step by step:\nFirst I created a new folder named [project name]\nNext I used these commands:\n cd [project name]\n git clone [remote project from github url]\n\nSo far I have created a folder and cloned a project that my group is working on in github.\nNext, I went inside that folder and created an angular project with\n ng new [angulartest]\n\nThis will create all the components of my angular test into the same folder that is the clone of the one from github.\nFinally, I pushed the new angular test on github with\n git add [angulartest]\n git commit\n git push\n\nWhat happens is that it only pushes the folder [angulartest] but none of its contents (even though there are contents in it). When I try to pull from its contents, I still just get an empty folder in return.\nWhen I try to enter that folder and add each element of the contents, using these steps:\n cd [angulartest]\n git add e2e, src, nodemodules, etc\n git commit\n git push\n\nIt gives me the following error (even when I try to add each element individually):\nfatal: in unpopulated submodule [angulartest]\nI was wondering if it was a problem with my git syntax, the angular project, or the way I tried to clone the project. That way, I know which direction I want to be headed when looking for a solution."
},
{
"role": "assistant",
"content": "It seems like, you may have removed the .git folder. In that case you can try \n git rm --cached angulartest -f"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-rev-list - Lists commit objects in reverse chronological order %(describe[:<options>])"
},
{
"role": "assistant",
"content": "human-readable name, like git-describe ; empty string for\nundescribable commits. The describe string may be followed by a colon and\nzero or more comma-separated options. Descriptions can be inconsistent when\ntags are added or removed at the same time. tags[=<bool-value>] : Instead of only considering annotated tags,\nconsider lightweight tags as well. abbrev=<number> : Instead of using the default number of hexadecimal digits\n(which will vary according to the number of objects in the repository with a\ndefault of 7) of the abbreviated object name, use <number> digits, or as many\ndigits as needed to form a unique object name. match=<pattern> : Only consider tags matching the given glob(7) pattern, excluding the \"refs/tags/\" prefix. exclude=<pattern> : Do not consider tags matching the given glob(7) pattern, excluding the \"refs/tags/\" prefix."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Is there a way to rollback my last push to Git? [duplicate]\nThis question already has answers here:\n \n \n\n\n\nClosed 12 years ago.\n\n\n\n\nPossible Duplicates:\nUndoing a 'git push' \n\nI have pushed some bad code, and I am the only user of the repository. How can I rollback my last commit?"
},
{
"role": "assistant",
"content": "Since you are the only user:\ngit reset --hard HEAD@{1}\ngit push -f\ngit reset --hard HEAD@{1}\n\n( basically, go back one commit, force push to the repo, then go back again - remove the last step if you don't care about the commit )\nWithout doing any changes to your local repo, you can also do something like:\ngit push -f origin <sha_of_previous_commit>:master\n\nGenerally, in published repos, it is safer to do git revert and then git push"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-update-index - Register file contents in the working tree to the index --[no-]ignore-skip-worktree-entries"
},
{
"role": "assistant",
"content": "Do not remove skip-worktree (AKA \"index-only\") entries even when\nthe --remove option was specified."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to connect to a remote Git repository?\nI am working with a team and we want to use Git (Not with GitHub, we have a private remote machine). We were using SVN until now.\nWe have a remote machine that works like an SVN repository.\nNow, we want to turn this machine into the Git central repository.\nBy what I have read, what everyone needs to do on their machines, is to install Git and use the following command to add the remote main repository:\ngit remote add origin <remote_repo_url>\n\nBut what is the remote_repo_url? How can I figure it out?\nOur remote machine has IP's like 189.14.666.666, in the remote machine I've installed Git and created a repository under C:\\MY_GIT_REPOSITORY. What should I put in the URL on the local machines?"
},
{
"role": "assistant",
"content": "It's simple and follow the small Steps to proceed:\n\nInstall git on the remote server say some ec2 instance\nNow create a project folder `$mkdir project.git\n$cd project and execute $git init --bare\n\nLet's say this project.git folder is present at your ip with address inside home_folder/workspace/project.git, forex- ec2 - /home/ubuntu/workspace/project.git\nNow in your local machine, $cd into the project folder which you want to push to git execute the below commands:\n\ngit init .\ngit remote add origin [email protected]:/home/ubuntu/workspace/project.git\ngit add .\ngit commit -m \"Initial commit\"\n\nBelow is an optional command but found it has been suggested as i was working to setup the same thing\n\ngit config --global remote.origin.receivepack \"git receive-pack\" \n\n\ngit pull origin master\ngit push origin master\n\nThis should work fine and will push the local code to the remote git repository.\nTo check the remote fetch url, cd project_folder/.git and cat config, this will give the remote url being used for pull and push operations.\nYou can also use an alternative way, after creating the project.git folder on git, clone the project and copy the entire content into that folder. Commit the changes and it should be the same way. While cloning make sure you have access or the key being is the secret key for the remote server being used for deployment."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-log - Show commit logs --stdin"
},
{
"role": "assistant",
"content": "In addition to getting arguments from the command line, read\nthem from standard input as well. This accepts commits and\npseudo-options like --all and --glob= . When a -- separator\nis seen, the following input is treated as paths and used to\nlimit the result. Flags like --not which are read via standard input\nare only respected for arguments passed in the same way and will not\ninfluence any subsequent command line arguments."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Git undo changes in some files [duplicate]\nThis question already has answers here:\n \n \n\n\n\n\nUndo working copy modifications of one file in Git\n\n (15 answers)\n \n\nClosed 6 years ago.\n\n\n\nWhile coding I added print statements into some files to keep track of what was going on.\nWhen I am done, is it possible to revert changes in some files, but commit the file I actually worked on? \nSay I added print in file A, but I modified file B. B is what I want to commit and A, I want to be set back to its old state."
},
{
"role": "assistant",
"content": "There are three basic ways to do this depending on what you have done with the changes to the file A. If you have not yet added the changes to the index or committed them, then you just want to use the checkout command - this will change the state of the working copy to match the repository:\ngit checkout A\n\nIf you added it to the index already, use reset:\ngit reset A\n\nIf you had committed it, then you use the revert command:\n# the -n means, do not commit the revert yet\ngit revert -n <sha1>\n# now make sure we are just going to commit the revert to A\ngit reset B\ngit commit\n\nIf on the other hand, you had committed it, but the commit involved rather a lot of files that you do not also want to revert, then the above method might involve a lot of \"reset B\" commands. In this case, you might like to use this method:\n# revert, but do not commit yet\ngit revert -n <sha1>\n# clean all the changes from the index\ngit reset\n# now just add A\ngit add A\ngit commit\n\nAnother method again, requires the use of the rebase -i command. This one can be useful if you have more than one commit to edit:\n# use rebase -i to cherry pick the commit you want to edit\n# specify the sha1 of the commit before the one you want to edit\n# you get an editor with a file and a bunch of lines starting with \"pick\"\n# change the one(s) you want to edit to \"edit\" and then save the file\ngit rebase -i <sha1>\n# now you enter a loop, for each commit you set as \"edit\", you get to basically redo that commit from scratch\n# assume we just picked the one commit with the erroneous A commit\ngit reset A\ngit commit --amend\n# go back to the start of the loop\ngit rebase --continue"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git - the stupid content tracker GIT_ASKPASS"
},
{
"role": "assistant",
"content": "If this environment variable is set, then Git commands which need to\nacquire passwords or passphrases (e.g. for HTTP or IMAP authentication)\nwill call this program with a suitable prompt as command-line argument\nand read the password from its STDOUT. See also the core.askPass option in git-config ."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "GITLAB CI Pipeline not triggered\n\nI have written this yml file for GitLab CI/CD. There is a shared runner configured and running.\nI am doing this first time and not sure where I am going wrong. The angular js project I am having\non the repo has a gulp build file and works perfectly on local machine. This code just has to trigger\nthat on the vm where my runner is present. On commit the pipeline does not show any job. Let me know what needs to be corrected!\nimage: docker:latest\n\ncache:\n paths:\n - node_modules/\n\ndeploy_stage:\n stage: build\n only:\n - master\n environment: stage\n script:\n - rmdir -rf \"build\"\n - mkdir \"build\"\n - cd \"build\"\n - git init\n - git clone \"my url\"\n - cd \"path of cloned repository\"\n - gulp build"
},
{
"role": "assistant",
"content": "What branch are you commiting to? You pipeline is configured to run only for commit on master branch.\n...\n only:\n - master\n...\n\nIf you want to have triggered jobs for other branches as well then remove this restriction from .gitlab-ci.yml file.\nDo not forget to Enable shared Runners (they may not be enabled by default), setting can be found on GitLab project page under Settings -> CI/CD -> Runners.\nUpdate: Did your pipeline triggers ever work for your project?\nIf not then I would try configuring simple pipeline just to test if triggers work fine:\ntest_simple_job:\n script:\n - echo I should execute for any pipeline trigger."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Git Bash won't let me type anything, just shows a blinking cursor\nI'm not able to type any characters at the Git-Bash command line; all it shows is a blinking cursor. Git Bash was working fine yesterday, but I'm not able to do anything on it now. What can I do to fix this?"
},
{
"role": "assistant",
"content": "I found the answer to a problem with similar symptoms. \nI'll include it here for someone who finds this page looking for an answer, as I did.\nIn my case, the cursor didn't move, or show my typing onscreen.\nHowever, it actually executed the command (if I pressed Enter), even though it looked like I didn't type anything in!\nThe solution was to type reset < Enter >\nTurns out it can be an issue for any shell program (cmd, git bash, etc), not necessarily just a Git Bash issue.\nIt looks like Ctrl-C or Ctrl-Z can occasionally result in the terminal not echoing commands to the screen, depending on what process was running at the time it was killed. \nreset restores it.\nI found the solution, and the explanation why, at https://askubuntu.com/a/172747/636571"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-show - Show various types of objects changes"
},
{
"role": "assistant",
"content": "Compute the dirstat numbers by counting the lines that have been\nremoved from the source, or added to the destination. This ignores\nthe amount of pure code movements within a file. In other words,\nrearranging lines in a file is not counted as much as other changes.\nThis is the default behavior when no parameter is given."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "gitglossary - A Git Glossary commit-ish (also committish)"
},
{
"role": "assistant",
"content": "A commit object or an object that\ncan be recursively dereferenced to a commit object.\nThe following are all commit-ishes:\na commit object,\na tag object that points to a commit\nobject,\na tag object that points to a tag object that points to a\ncommit object,\netc."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-format-patch - Prepare patches for e-mail submission --[no-]force-in-body-from"
},
{
"role": "assistant",
"content": "With the e-mail sender specified via the --from option, by\ndefault, an in-body \"From:\" to identify the real author of\nthe commit is added at the top of the commit log message if\nthe sender is different from the author. With this option,\nthe in-body \"From:\" is added even when the sender and the\nauthor have the same name and address, which may help if the\nmailing list software mangles the sender’s identity.\nDefaults to the value of the format.forceInBodyFrom configuration variable."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git - the stupid content tracker git-interpret-trailers"
},
{
"role": "assistant",
"content": "Add or parse structured information in commit messages"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-log - Show commit logs --[no-]mailmap --[no-]use-mailmap"
},
{
"role": "assistant",
"content": "Use mailmap file to map author and committer names and email\naddresses to canonical real names and email addresses. See git-shortlog ."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-show - Show various types of objects --output=<file>"
},
{
"role": "assistant",
"content": "Output to a specific file instead of stdout."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-format-patch - Prepare patches for e-mail submission"
},
{
"role": "assistant",
"content": "CAVEATS Note that format-patch will omit merge commits from the output, even\nif they are part of the requested range. A simple \"patch\" does not\ninclude enough information for the receiving end to reproduce the same\nmerge commit."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-describe - Give an object a human readable name based on an available ref --first-parent"
},
{
"role": "assistant",
"content": "Follow only the first parent commit upon seeing a merge commit.\nThis is useful when you wish to not match tags on branches merged\nin the history of the target commit."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to prevent many git conflicts when rebasing many commits?\nStory: in the middle of a project my colleague created a new branch from master and started doing her heavy re-factoring work. I created my branch from master and started doing new stuff on the page. We are committing regularly, but only I can rebase code to master (because colleagues changes are too heavy and cannot be deployed from master yet). Unfortunately some of our work rely on the same files. So after few days of work when she finally wanted to rebase her changes to master, she had a lot of git conflicts. \nmy_branch #---#----#-#-------#----#--#-----#---#----#----#\n / \\ \\ \\ \\ \\ \\\nmaster *-------*--------------*---*---*--------------*----*----*\n \\ /\nher branch #------#-------#-----------#-----------#------------#\n\nQuestion 1 is: how to prevent lot of git conflicts when we are working on same files? (or what is the best practice in this situation?)\nbut this isn't the end of our question, ...to be absolutely correct she tried to do rebase from master to her branch (to have changes I committed), so the commit map should look something like this \nmy_branch #---#----#-#-------#----#--#-----#---#----#----#\n / \\ \\ \\ \\ \\ \\\nmaster *-------*--------------*---*---*--------------*----*----*\n \\ \\ \\ /\nher branch #------#-------#----*------#-----*-----#------------#\n\nAnd this is what is bothering us. During these rebases she was fixing those conflicts. But git doesn't remember her decision on conflict fix, so when she did another git rebase from master to her-branch she had to fix the same git conflicts again that she was fixing in previous rebases.\nQuestion 2 is: how to tell git to remember git conflict fix after git rebase from master branch, so after next rebase we don't have to fix the same conflicts again?"
},
{
"role": "assistant",
"content": "Fortunately, git has a mechanism for dealing with exactly this problem called git rerere - essentially, if you have git rerere enabled, then each time your resolve a conflict the fact that you resolved that exact conflict in a particular way is remembered. If the same conflict comes up again, the same resolution is automatically used. There are some helpful articles below:\n\nhttp://scottchacon.com/2010/03/08/rerere.html (blog post)\nhttp://git-scm.com/docs/git-rerere.html (manual entry)\nAre there any downsides to enabling git rerere? (question in stackoverflow)\nhttp://progit.org/2010/03/08/rerere.html (original answer link: seems broken)\n\n... but essentially you can just do:\ngit config --global rerere.enabled 1\n\n... and forget about it, while enjoying easier rebasing / merging :)"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-rev-list - Lists commit objects in reverse chronological order %ad"
},
{
"role": "assistant",
"content": "author date (format respects --date= option)"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "What is \"Developer Program Member\" on Github.com\n\nI have seen couple of Github profiles having \"Developer Program Member\". I searched on Google a lot but not able to find how people get that in their profile."
},
{
"role": "assistant",
"content": "This is for developers registered to the GitHub Developer Program (like this GitHub profile, for instance)\n\nMembership is open to individual developers and companies who have:\n\nA paid GitHub.com personal or organization plan\n (since 2019, you don't need a paid membership anymore)\nAn integration in production or development using the GitHub API\nAn email address where GitHub users can contact you for support\n\n\nThat allows for:\n\nStaying in the know:\nBe the first to know about API changes and try out new features before they launch.\nScratching an itch\nBuild your own tools that seamlessly integrate with the place you push code every day.\nTaking on the enterprise\nObtain developer licenses to build and test your application against GitHub Enterprise."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to stop git from making files non-executable on cygwin?\nI use git on Windows via cygwin and soon decided to use filemode=false (since otherwise I've got a lot of changes after the initial git clone). I'm definitely not interested in tracking permission at all, the only think I need is for some files to be executable. From time to time, I find that the x flag on some files gets lost and I strongly suppose it's because of git.\nI'd be happy with a solution allowing to execute chmod a+x ... when needed."
},
{
"role": "assistant",
"content": "I believe you want git update-index --chmod=+x <file>, followed by a commit."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "'<Branch>' is already checked out at '</other/location>' in git worktrees\nI started using git worktrees. It seems to work, but I'm getting this error when attempting to check out a branch in the cloned worktree:\nfatal: '<branch>' is already checked out at '</other/location>'\n\nHow do I get around this without deleting the .git/worktrees directory?"
},
{
"role": "assistant",
"content": "Git won't let you check out the same branch twice, because if you do, and then go to one of the two work-trees and make a new commit, you'll set yourself up for misery when you go back to the other work-tree.\nIf you have actually removed the other work-tree, simply run git worktree prune to make Git realize this. If you have not actually removed the other work-tree, don't check it out twice: it's no fun."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-filter-branch - Rewrite branches"
},
{
"role": "assistant",
"content": "EXIT STATUS On success, the exit status is 0 . If the filter can’t find any commits to\nrewrite, the exit status is 2 . On any other error, the exit status may be\nany other non-zero value."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-diff - Show changes between commits, commit and working tree, etc --no-color-moved-ws"
},
{
"role": "assistant",
"content": "Do not ignore whitespace when performing move detection. This can be\nused to override configuration settings. It is the same as --color-moved-ws=no ."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git replace local version with remote version\nHow can I tell git to ignore my local file and take the one from my remote branch without trying to merge and causing conflicts?"
},
{
"role": "assistant",
"content": "This is the safest solution:\ngit stash\n\nNow you can do whatever you want without fear of conflicts.\nFor instance:\ngit checkout origin/master # or origin/main\n\nIf you want to include the remote changes in the master branch you can do:\ngit reset --hard origin/master # or origin/main\n\nThis will make you branch \"master\" to point to \"origin/master\"."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-send-email - Send a collection of patches as emails --[no-]thread"
},
{
"role": "assistant",
"content": "If this is set, the In-Reply-To and References headers will be\nadded to each email sent. Whether each mail refers to the\nprevious email ( deep threading per git format-patch wording) or to the first email ( shallow threading) is\ngoverned by \"--[no-]chain-reply-to\". If disabled with \"--no-thread\", those headers will not be added\n(unless specified with --in-reply-to). Default is the value of the sendemail.thread configuration value; if that is unspecified,\ndefault to --thread. It is up to the user to ensure that no In-Reply-To header already\nexists when git send-email is asked to add it (especially note that git format-patch can be configured to do the threading itself).\nFailure to do so may not produce the expected result in the\nrecipient’s MUA."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Switch to another Git tag\nHow do I check out version version/tag 1.1.4 of the rspec bundle?\ncd ~/Library/Application\\ Support/TextMate/Bundles/\ngit clone git://github.com/rspec/rspec-tmbundle.git RSpec.tmbundle\nosascript -e 'tell app \"TextMate\" to reload bundles'"
},
{
"role": "assistant",
"content": "Clone the repository as normal:\ngit clone git://github.com/rspec/rspec-tmbundle.git RSpec.tmbundle\n\nThen checkout the tag you want like so:\ngit checkout tags/1.1.4\n\nThis will checkout out the tag in a 'detached HEAD' state. In this state, \"you can look around, make experimental changes and commit them, and [discard those commits] without impacting any branches by performing another checkout\".\nTo retain any changes made, move them to a new branch:\ngit checkout -b 1.1.4-jspooner\n\nYou can get back to the master branch by using:\ngit checkout master\n\nNote, as was mentioned in the first revision of this answer, there is another way to checkout a tag:\ngit checkout 1.1.4\n\nBut as was mentioned in a comment, if you have a branch by that same name, this will result in git warning you that the refname is ambiguous and checking out the branch by default:\nwarning: refname 'test' is ambiguous.\nSwitched to branch '1.1.4'\n\nThe shorthand can be safely used if the repository does not share names between branches and tags."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "In git, is there a simple way of introducing an unrelated branch to a repository?\nWhile helping a friend with a git problem today, I had to introduce a\nbranch that needed to be totally separate from the master branch.\nThe contents of this branch really had a different origin from what\nhad been developed on the master branch, but they were going to be\nmerged into the master branch at a later time.\nI remembered from reading John Wiegley's Git from the bottom\nup how\nbranches are essentially a label to a commit that follows a certain\nconvention and how a commit is tied to a tree of files and, optionally\nto parent commits. We went to create a parentless commit to the\nexisting repository using git's plumbing:\nSo we got rid of all files in the index ...\n$ git rm -rf .\n\n... extracted directories and files from a tarball, added those to the\nindex ...\n$ git add .\n\n... and created a tree object ...\n$ git write-tree\n\n(git-write-tree told us the sha1sum of the created tree object.)\nThen, We committed the tree, without specifying parent commits...\n$ echo \"Imported project foo\" | git commit-tree $TREE\n\n(git-commit-tree told us the sha1sum of the created commit object.)\n... and created a new branch that points to our newly created\ncommit.\n$ git update-ref refs/heads/other-branch $COMMIT\n\nFinally, we returned to the master branch to continue work there.\n$ git checkout -f master\n\nThis seems to have worked as planned. But this is clearly not the kind\nof procedure I would recommend to someone who is just getting started\nusing git, to put it mildly. Is there an easier way of creating a\nnew branch that is entirely unrelated to everything that has happened\nin the repository so far?"
},
{
"role": "assistant",
"content": "There is a new feature (since V1.7.2) which makes this task a little more high-level than what's in any of the other answers.\ngit checkout now supports the --orphan option. From the man page:\ngit checkout [-q] [-f] [-m] --orphan <new_branch> [<start_point>]\n\nCreate a new orphan branch, named\n <new_branch>, started from\n <start_point> and switch to it. The\n first commit made on this new branch\n will have no parents and it will be\n the root of a new history totally\n disconnected from all the other\n branches and commits.\n\nThis doesn't do exactly what the asker wanted, because it populates the index and the working tree from <start_point> (since this is, after all, a checkout command). The only other action necessary is to remove any unwanted items from the working tree and index. Unfortunately, git reset --hard doesn't work, but git rm -rf . can be used instead (I believe this is equivalent to rm .git/index; git clean -fdx given in other answers).\n\nIn summary:\ngit checkout --orphan newbranch\ngit rm -rf .\n<do work>\ngit add your files\ngit commit -m 'Initial commit'\n\nI left <start_point> unspecified because it defaults to HEAD, and we don't really care anyway. This sequence does essentially the same thing as the command sequence in Artem's answer, just without resorting to scary plumbing commands."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-status - Show the working tree status"
},
{
"role": "assistant",
"content": "UNTRACKED FILES AND PERFORMANCE git status can be very slow in large worktrees if/when it\nneeds to search for untracked files and directories. There are\nmany configuration options available to speed this up by either\navoiding the work or making use of cached results from previous\nGit commands. There is no single optimum set of settings right\nfor everyone. We’ll list a summary of the relevant options to help\nyou, but before going into the list, you may want to run git status again, because your configuration may already be caching git status results, so it could be faster on subsequent runs. The --untracked-files=no flag or the status.showUntrackedFiles=no config (see above for both):\nindicate that git status should not report untracked\nfiles. This is the fastest option. git status will not list\nthe untracked files, so you need to be careful to remember if\nyou create any new files and manually git add them. advice.statusUoption=false (see git-config ):\nsetting this variable to false disables the warning message\ngiven when enumerating untracked files takes more than 2\nseconds. In a large project, it may take longer and the user\nmay have already accepted the trade off (e.g. using \"-uno\" may\nnot be an acceptable option for the user), in which case, there\nis no point issuing the warning message, and in such a case,\ndisabling the warning may be the best. core.untrackedCache=true (see git-update-index ):\nenable the untracked cache feature and only search directories\nthat have been modified since the previous git status command.\nGit remembers the set of untracked files within each directory\nand assumes that if a directory has not been modified, then\nthe set of untracked files within has not changed. This is much\nfaster than enumerating the contents of every directory, but still\nnot without cost, because Git still has to search for the set of\nmodified directories. The untracked cache is stored in the .git/index file. The reduced cost of searching for untracked\nfiles is offset slightly by the increased size of the index and\nthe cost of keeping it up-to-date. That reduced search time is\nusually worth the additional size. core.untrackedCache=true and core.fsmonitor=true or core.fsmonitor=<hook-command-pathname> (see git-update-index ): enable both the untracked cache\nand FSMonitor features and only search directories that have\nbeen modified since the previous git status command. This\nis faster than using just the untracked cache alone because\nGit can also avoid searching for modified directories. Git\nonly has to enumerate the exact set of directories that have\nchanged recently. While the FSMonitor feature can be enabled\nwithout the untracked cache, the benefits are greatly reduced\nin that case. Note that after you turn on the untracked cache and/or FSMonitor\nfeatures it may take a few git status commands for the various\ncaches to warm up before you see improved command times. This is\nnormal."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Remove trailing whitespace on save in IntelliJ IDEA 12\nIs it possible to remove trailing whitespace automatically on save in IntelliJ IDEA? I know there are some workarounds, for example, using git to trim the whitespace on commit. \nMaybe this question is a duplicate of this one, but i hope this can be done without setting up keyboard shortcuts and macros."
},
{
"role": "assistant",
"content": "Don't know about 12, but there's the following setting in 13:\nSettings → Editor → Strip trailing spaces on Save\nAs of IntelliJ 2017.2 it's under\nSettings → Editor → General → Strip trailing spaces on Save"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to parse link header from github API\n\nthe github API sends the pagination data for the json results in the http link header:\nLink: <https://api.github.com/repos?page=3&per_page=100>; rel=\"next\",\n<https://api.github.com/repos?page=50&per_page=100>; rel=\"last\"\n\nsince the github API is not the only API using this method (i think) i wanted to ask if someone has a useful little snippet to parse the link header (and convert it to an array for example) so that i can use it for my js app.\ni googled around but found nothing useful regarding how to parse pagination from json APIs"
},
{
"role": "assistant",
"content": "The parse-link-header NPM module exists for this purpose; its source can be found on github under a MIT license (free for commercial use).\nInstallation is as simple as:\nnpm install parse-link-header\n\nUsage looks like the following:\nvar parse = require('parse-link-header');\nvar parsed = parse('<https://api.github.com/repos?page=3&per_page=100>; rel=\"next\", <https://api.github.com/repos?page=50&per_page=100>; rel=\"last\"')\n\n...after which one has parsed.next, parsed.last, etc:\n{ next:\n { page: '3',\n per_page: '100',\n rel: 'next',\n url: 'https://api.github.com/repos?page=3&per_page=100' },\n last:\n { page: '50',\n per_page: '100',\n rel: 'last',\n url: ' https://api.github.com/repos?page=50&per_page=100' } }"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git get short hash from regular hash\n\nI have a regular long SHA-1 hash string. I would like to get the shortest unambiguous SHA-1 hash string version of it. That is, the one I would get by using git log -1 --pretty=format:%h, assuming the long hash refers to the last commit."
},
{
"role": "assistant",
"content": "The shortest SHA1 you can get has a length of 4. Rev parse will give you a SHA1 of 7 digits by default with the short option :\ngit rev-parse --short 921103db8259eb9de72f42db8b939895f5651489\n921103d\n\nYou have to specify 4 to the short option to have the shortest unambiguous SHA1 :\ngit rev-parse --short=4 921103db8259eb9de72f42db8b939895f5651489\n92110\n\nYou can also set it in the core.abbrev configuration variable."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How do I properly remove sensitive data pushed to a Git repo?\nI pushed a file containing a password to my repo by mistake - FYI the repo is just a small personal project.\nOnce I realised the password was present I added the file to .gitignore and executed git rm -r --cached <filename>, committed and pushed to the repo.\nI now realise the password is still present in the history - what is the best way to remove it?\nI read the Remove sensitive data page on Github which suggests changing the password - which I have done - but I would like to remove the history as well."
},
{
"role": "assistant",
"content": "Since you have already made 5 commits since the commit containing the clear text password, you best bet is to do a git rebase -i in interactive mode on your local branch. Find the SHA-1 of the commit where you added the clear text password, and type the following:\ngit rebase --interactive dba507c^\n\nwhere dba507c are the first 7 characters of the SHA-1 for the bad commit.\nChange this:\npick dba507c comment for commit containing clear text password\n\nTo this:\nedit dba507c I have removed the clear text password\n\nMake the change to the password file to remove the clear text, then commit your result like this:\ngit commit --all --amend --no-edit\ngit rebase --continue\n\nFinish the rebase, then push your (correct) local branch to the remote via:\ngit push -f origin your_branch\n\nYou will need to force push your_branch because you have rewritten history (by modifying the password file). Now you have all your latest commits, but you have removed the clear text."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-read-tree - Reads tree information into the index --trivial"
},
{
"role": "assistant",
"content": "Restrict three-way merge by git read-tree to happen\nonly if there is no file-level merging required, instead\nof resolving merge for trivial cases and leaving\nconflicting files unresolved in the index."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Git submodules not updating in Jenkins build\nI have a submodule in a project in Jenkins. I've enabled the advanced setting to recursively update submodules.\nWhen I run the build, I see that the workspace has the files from the submodule. The problem is, it seems to be the first revision of the submodule. When I push changes (repository hosted on GitHub) Jenkins doesn't seem to update the submodule to get the right changes. Has anyone ever seen this?"
},
{
"role": "assistant",
"content": "Note that the Jenkins Git plugin 2.0 will have \"advance submodule behaviors\", which should ensure proper updates of the submodules:\n\nAs commented by vikramvi:\n\nAdvanced sub-modules behavior > \"Path of the reference repo to use during submodule update\" against this field , add submodule git url.\n\n\n\nOwen B mentions in the comments:\n\nFor the authentication issue, there's now a \"Use credentials from default remote of parent repository\" option\n\nSeen here in JENKINS-20941:"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-difftool - Show changes using common diff tools difftool.<tool>.cmd"
},
{
"role": "assistant",
"content": "Specify the command to invoke the specified diff tool.\nThe specified command is evaluated in shell with the following\nvariables available: LOCAL is set to the name of the temporary\nfile containing the contents of the diff pre-image and REMOTE is set to the name of the temporary file containing the contents\nof the diff post-image. See the --tool=<tool> option in git-difftool for more details."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to convert a readonly git clone from github to a forked one\nFrom time to time I encounter this issue.\nLet's say that I did following to read the source code of rails because I am running into some issues.\ngit clone git://github.com/rails/rails.git\n\nDuring the research I tested something and now I have a fix I would like rails core team to take a look at. How do I push my changes to a forked version of rails.\nRemember when I cloned, I did not clone a forked version but a read-only version.\nIt is not that I am opposed to forking. It is just that sometimes I think I am just going to browse then I want to add something."
},
{
"role": "assistant",
"content": "When you clone a repo, it automatically sets up a remote called origin which refers to the repo that you have cloned. This is now pointing to the upstream Rails project, but what you need is to create your own fork that you can push to, and then set up a remote that points there so you can push to it.\nThe first step is to click the \"Fork\" button on the upstream GitHub project page (picture from GitHub instructions on forking):\n\nOnce you've done that, find and copy the URL for that repo. Make sure you use the SSH URL, which has read and write access. It should be something like [email protected]:nadal/rails.git, assuming your user name is nadal.\nNow you can create the remote, which allows Git to keep track of a remote repository, pulling from it or pushing to it depending on the access you have. You can choose to either replace origin with the one that you will push to (which is how many people have it set up), or leave origin pointing to upstream and instead create a new remote. I'll show how to do the first setup; the second should be easy to figure out.\nTo change origin to point to your fork on GitHub, you will probably want to keep the upstream branch around somewhere, so rename it to upstream:\ngit remote rename origin upstream\n\nNow create a new remote pointing to your fork:\ngit remote add -f origin [email protected]:nadal/rails.git\n\nAnd now you should be able to push to your new fork:\ngit push origin master\n\nOnce you are happy with the changes you've pushed up to GitHub, and would like someone from the Rails team to look at it, you have two choices. One is to send a pull request using GitHub; see the docs there for how to do that. If you only have one or a few small patches, however, the Rails team would prefer that you create a Lighthouse ticket and attach you patch; see the instructions on contributing to Rails for more information.\nedit Here's a diagram to indicate what's going on. What you have done is simply clone the upstream rails repo; so now you have your own repo on your own machine, which refers to git://github.com/rails/rails.git as origin:\n\nGithub: git://github.com/rails/rails.git\n ^\n |\nRemotes: origin\n |\nYour machine: rails/\n\nHere's what you get if you forked and then clone your fork:\n\nGithub: git://github.com/rails/rails.git <-- [email protected]:nadal/rails.git\n ^\n |\nRemotes: origin\n |\nYour machine: rails/\n\nIf you follow my instructions, here is what you will get:\n\nGithub: git://github.com/rails/rails.git <-- [email protected]:nadal/rails.git\n ^ ^\n | |\nRemotes: upstream origin\n | |\nYour machine: \\-------------------------------rails/\n\nWhich is just like the version that you get by forking, except that it also has an upstream remote so you can track official changes and merge them in to your code (if you had created the forked version, you would probably want to add the upstream remote as well)."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Git push --force from IntelliJ IDEA\nIt seems that the force option was removed from the pushing dialog. I am currently using IntelliJ IDEA 13.1.1 and I cannot find any way how to push with force option. I tried to search the documentation and it seems that in version 10 the force option was still there. Do you maybe know how to push with force from IntelliJ IDEA?"
},
{
"role": "assistant",
"content": "Since IntelliJ IDEA 14 update it's possible to enable a checkbox for exactly that, you first have to enable \"Allow force push\" in Settings->Version Control->Git.\n2018 Update: To allow force push on master branch, look for \"protected branches\" in Git settings -> Then delete value \"master\"."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Jenkins: Failed to connect to repository\nI'm trying to connect jenkins on a github repo.\nWhen I specify the Repo URL jenkins return the following error message: \n\nFailed to connect to repository : Command \"git ls-remote -h [email protected]:adolfosrs/jenkins-test.git HEAD\" returned status code 128:\n stdout:\n stderr: Host key verification failed.\n fatal: Could not read from remote repository.\n Please make sure you have the correct access rights\n and the repository exists.\n\nWhen using the HTTPS:// Url jenkins returns:\n\nFailed to connect to repository : Failed to connect to\n https://github.com/adolfosrs/jenkins-test.git (status = 407)\n\nI could successfully clone the repo at the same machine where jenkins is running and I also run the git ls-remote -h [email protected]:adolfosrs/jenkins-test.git HEAD command. So I have the right SSH at github."
},
{
"role": "assistant",
"content": "The problem was that somehow I created the ssh files with the root user.\nSo the files owner was root. \nThe solution was just change the ownership to the jenkins user. \nchown jenkins id_rsa.pub \nchown jenkins id_rsa"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git - the stupid content tracker git-write-tree"
},
{
"role": "assistant",
"content": "Create a tree object from the current index"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to get diff working like git-diff?\nI like the output formatting of git diff. The color and the +/- representation of changes between lines is easier to read than GNU diff.\nI can run git diff using --no-index flag outside of a git repo and it works fine. However, it appears to be missing the --exclude option for excluding files or subdirectories from a recursive diff. \nIs there a way to get the best of both worlds? (color options and +/- format of git diff and --exclude option of GNU diff). \nI've experimented with colordiff, but I still prefer the output format of git diff"
},
{
"role": "assistant",
"content": "This will do the +/- rather than < and >.\ndiff -u file1 file2\n\nSince GNU diffutils 3.4 the flag --color has been added. Combining both makes the following:\ndiff --color -u file1 file2\n\nThe flag --color also takes an argument, valid options are never, always, or auto. Useful when you want to be more explicit on what needs to be done."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How can I retrieve the remote Git address of a repository?\nHow can I retrieve the remote Git address of a repository?\nI tried git remote, but that just lists the branches."
},
{
"role": "assistant",
"content": "When you want to show an URL of remote branches, try:\ngit remote -v"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Git/GitHub can't push to master\n\nI am new to Git/GitHub and ran into an issue. I created a test project and added it to the local repository. Now I am trying to add files/project to the remote repository.\nHere's what I did (and this worked) -\ngit remote add origin git://github.com/my_user_name/my_repo.git\n\nNow when I try to push the repository to GitHub, using the following command, I get the following error -\ngit push origin master\n\nError -\nfatal: remote error:\nYou can't push to git://github.com/my_user_name/my_repo.git\nUse [email protected]:my_user_name/my_repo.git"
},
{
"role": "assistant",
"content": "GitHub doesn't support pushing over the Git protocol, which is indicated by your use of the URL beginning git://. As the error message says, if you want to push, you should use either the SSH URL [email protected]:my_user_name/my_repo.git or the \"smart HTTP\" protocol by using the https:// URL that GitHub shows you for your repository.\n(Update: to my surprise, some people apparently thought that by this I was suggesting that \"https\" means \"smart HTTP\", which I wasn't. Git used to have a \"dumb HTTP\" protocol which didn't allow pushing before the \"smart HTTP\" that GitHub uses was introduced - either could be used over either http or https. The differences between the transfer protocols used by Git are explained in the link below.)\nIf you want to change the URL of origin, you can just do:\ngit remote set-url origin [email protected]:my_user_name/my_repo.git\n\nor\ngit remote set-url origin https://github.com/my_user_name/my_repo.git\n\nMore information is available in 10.6 Git Internals - Transfer Protocols."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git clone error: RPC failed; curl 56 OpenSSL SSL_read: SSL_ERROR_SYSCALL, errno 10054\n\nI'm having trouble cloning a repo on git. I've been trying for to days and have tried quite a few solutions (in most the problem was slightly different but seemed to apply) but nothing has done anything to make a difference.\nI've tried switching off the anti-virus and firewall but that didn't help.\nI've also tried uninstalling and reinstalling the network adapter drivers (and restarting the computer) and that didn't work.\nFrom what I understand it's a network issue somewhere as the remote server keeps hanging up but I'm not managing to get anywhere with the issue.\nUsing git clone -v --progress seemed to give the same output as git clone.\nOutput from git clone -v --progress https://github.com/mit-cml/appinventor-sources.git\n\nCloning into 'appinventor-sources'...\n POST git-upload-pack (gzip 1425 to 774 bytes)\n remote: Counting objects: 41649, done.\n remote: Compressing objects: 100% (7/7), done.\n error: RPC failed; curl 56 OpenSSL SSL_read: SSL_ERROR_SYSCALL, errno 10054\n fatal: The remote end hung up unexpectedly\n fatal: early EOF\n fatal: index-pack failed \n\nI've now tried increasing the buffer again \n\ngit config --global http.postBuffer 1048576000\n\nbut still nothing.\nI'm following the solution from The remote end hung up unexpectedly while git cloning for troubleshooting."
},
{
"role": "assistant",
"content": "I resolved the same problem by this:\ngit config http.postBuffer 524288000\n\nIt might be because of the large size of the repository and the default buffer size of git so by doing above (on git bash), git buffer size will be increased."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-rebase - Reapply commits on top of another base tip --committer-date-is-author-date"
},
{
"role": "assistant",
"content": "Instead of using the current time as the committer date, use\nthe author date of the commit being rebased as the committer\ndate. This option implies --force-rebase ."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to push to a non-bare Git repository?\nI usually work on a remote server via ssh (screen and vim), where I have a Git repository. Sometimes I'm not online, so I have a separate repository (cloned from my remote) on my laptop.\nHowever, I can't pull from this repository on remote side because I'm usually behind a firewall or I don't have a public IP.\nI've read that I should push just to a bare repository. How should I then push my changes to my remote repository?"
},
{
"role": "assistant",
"content": "Best Option\nProbably the cleanest, least confusing, and safest way to push into your non-bare remote repository, is to push to dedicated branches in the remote that represent your laptop branches.\nLet's look at the simplest case, and assume you have just one branch in each repo: master. When you push to the remote repo from your laptop, instead of pushing master -> master, push master -> laptop-master (or a similar name). This way the push doesn't affect the currently checked-out master branch in the remote repo. To do this from the laptop, the command is pretty simple:\ngit push origin master:laptop-master\n\nThis means that the local master branch will be pushed to the branch named \"laptop-master\" in the remote repository. In your remote repo, you'll have a new branch named \"laptop-master\" that you can then merge into your remote master when you are ready.\nAlternate Option\nIt's also possible to just push master -> master, but pushing to the currently checked-out branch of a non-bare repo is generally not recommended, because it can be confusing if you don't understand what is going on. This is because pushing to a checked-out branch doesn't update the work tree, so checking git status in the checked-out branch that was pushed into will show exactly the opposite differences as what was most recently pushed. It would get especially confusing if the work tree was dirty before the push was done, which is a big reason why this is not recommended.\nIf you want to try just pushing master -> master, then the command is just:\ngit push origin\n\nBut when you go back to the remote repo, you'll most likely want to do a git reset --hard HEAD to get the work tree in sync with the content that was pushed. This can be dangerous, because if there are any uncommitted changes in the remote work tree that you wanted to keep it will wipe them out. Be sure you know what the consequences of this are before you try it, or at least make a backup first!\nEDIT Since Git 2.3, you can use \"push-to-deploy\" git push: https://github.com/blog/1957-git-2-3-has-been-released. But pushing to a separate branch and then merging is usually better since it does an actual merge (hence works with uncommitted changes just like merge does)."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "GitHub changes repository to the wrong language\n\nI know this isn't a huge deal, but I like my GitHub to be linguistically diversified. I wrote a project in Swift and when I commit it says it's in Objective-C.\nI think it might be because the Parse frameworks are written in Objective-C and it detects that, but is there a way to change the display language on the main repository page?"
},
{
"role": "assistant",
"content": "I found the simplest thing was to create a file called .gitattributes in the root folder of my repository, and give it these contents:\n* linguist-vendored\n*.js linguist-vendored=false\n\nThis example tells GitHub/Linguist to ignore all files, and then just look at .js files. My project, https://github.com/aim12340/jQuery-Before-Ready, was listed as HTML because the HTML example files were bigger than the JavaScript files. This file fixes it for me and now it's listed as JavaScript."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git clone works; git submodule fails \"Permission denied\"\n\nOn a private repository from gitlab, when I run git clone [email protected]:group/project-submodule.git the clone completes successfully.\nAs part of the cloning process, I'm asked for the passphrase of my private key.\nWhen I run\nsubmodule update --init \"group/project-submodule\"\nIt fails with: \n\nPermission denied, please try again.\n Permission denied, please try again.\n Permission denied (publickey,gssapi-keyex,gssapi-with-mic,password).\n fatal: Could not read from remote repository.\n\nWhile trying to process the submodule getting, I'm not asked for the passphrase for my private key.\n(I had to anonymize it)\n\nfatal: clone of '[email protected]:group/project-submodule.git' into submodule path 'C:/Users/user/repos/project-module/project-submodule' failed\n\nI've checked the .gitmodules file and it contains the right data (I think it can be confirmed by the error message).\nThe main element that calls my attention is that I'm not asked for my private key passphrase. Even weirder because, when I use git clone directly, it runs as expected.\nI also already diagnosed by accessing with ssh and it asks me for the passphrase just like it happens when I execute a pull or a clone\nUsing git for windows \"git version 2.16.2.windows.1\""
},
{
"role": "assistant",
"content": "Git tries to clone the submodule using ssh and not https.\nIf you haven't configured your ssh key this will fail.\nYou can setup ssh-agent to cache the password for the ssh key and get git to use that. Or change to https.\nGit is a bit confusing regarding submodules. They are configured in the .gitmodules file in the directory, but changing the url here from ssh to https won't help. Git uses the url that is configured in .git/config.\nOpen this file and you will find something like this.\n[submodule \"project-submodule\"]\n url = [email protected]:project-submodule.git\n\nChange this url to the https equivalent and try again."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-diff-index - Compare a tree to the working tree or index --binary"
},
{
"role": "assistant",
"content": "In addition to --full-index , output a binary diff that\ncan be applied with git-apply .\nImplies --patch ."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "gitfaq - Frequently asked questions about using Git"
},
{
"role": "assistant",
"content": "SYNOPSIS gitfaq"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Backup a GitHub repository\nWhat is the best way to create a local backup of a git repository hosted on GitHub, given the following requirements?:\n\nThe local backup should be a bare repo.\nThe backup should include all branches.\nIt should be easy to (incrementally) update the backup.\n\nBasically, I want a perfect mirror, with the possibility to update easily. As such, the command\ngit clone --mirror git://github.com/...\n\ncomes to mind, but as far as I can tell, that doesn't allow for an easy update (I'd have to delete and recreate my local backup). Also, the mirror option for git clone seems quite recent, I don't have it on some of the systems I'm working on (which have slightly older versions of git running).\nWhat is your recommended solution for this kind of problem?"
},
{
"role": "assistant",
"content": "I am not sure it could cover all your requirements, but you could check out git bundle\ngit bundle\n\n\nThis command provides support for git fetch and git pull to operate by packaging objects and references in an archive at the originating machine, then importing those into another repository using git fetch and git pull after moving the archive by some means\n\nWhat I like about that solution is the single file produced, with exactly what I want in it\n\ngit bundle will only package references that are shown by git-show-ref: this includes heads, tags, and remote heads.\n\nmachineA$ git bundle create file.bundle master\n\n\nNote: Kent Fredric mentions in the comments a subtlety from git rev-list:\n--all\n\n\nPretend as if all the refs in $GIT_DIR/refs/ are listed on the command line as <commit>.\n\nHe adds:\n\nyour current bundle will only bundle parents of the commit, you'd probably need to specify --all to get a complete bundle of everything (branches that are descendant of master).\n\nTo see the difference:\n$ git bundle create /tmp/foo master\n$ git bundle create /tmp/foo-all --all\n$ git bundle list-heads /tmp/foo\n$ git bundle list-heads /tmp/foo-all"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "In Git, how do I diff to the first commit of my branch?\nI've made several commits to a local branch, but I'm not sure what the best way to diff what I currently have to my branch's starting state. I know I can do something like git diff HEAD HEAD~6 if there's been 6 commits to my branch, but I was hoping for something that was independent of the number of commits.\nEdit:\nI failed to mention this: I was hoping I wouldn't have to dig through the log to get the hash of the commit I branched from. If I had 80 commits for example, this wouldn't be a fun task.\nAlso, presume that the original branch I branched from has already had several changes."
},
{
"role": "assistant",
"content": "You'll want to use the triple dot syntax described in git help diff:\ngit diff otherbranch...\n\nThis is the same as:\ngit diff otherbranch...HEAD\n\nwhich is the same as:\ngit diff $(git merge-base otherbranch HEAD) HEAD\n\nThe merge-base command prints the \"best\" (most recent) common ancestor, so the above command shows the difference from the most recent commit that HEAD has in common with otherbranch to HEAD.\nNote you can use @{u} in place of otherbranch to see the changes you made since you diverged from the upstream branch. See git help revisions for details about the syntax."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-show - Show various types of objects %n"
},
{
"role": "assistant",
"content": "newline"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How can I rewrite python __version__ with git?\nI would like to define a __version__ variable in my module which should be automatically updated on git commit similarly to what SVN keywords do. Is there a way to achieve it in Git? Does anyone have a working example?\nI considered using GitPython, but I would not like to introduce another dependency and I want users who download the module from SVN repo or as a zip package to have the same versioning scheme (I do not care that is some illegible hash).\nEdit: My particular problem is that I have to run simulations whose result depend on the exact version of the simulation script. Therefore each time I have to store version number together with the simulation results. If both run out of sync, it may have very dire outcomes."
},
{
"role": "assistant",
"content": "It might be better to do this as part of your packaging, rather than after every commit.\nThere are two primary options:\n\nUse git-archive to package, and use the export-subst attribute. Unfortunately, the things you can substitute in are limited to the placeholders from git log --format=.... For example, you could write __version__ = $Format:%H$ in your file, put <filename> export-subst in your .gitattributes, and when you run git archive, that'd be changed to the full hash of the commit you're archiving with. This is just about what you're asking for, but I do prefer the next option.\nDo it yourself as part of a packaging process (often a build process for compiled packages), and use git describe. That will get you a nice pretty string like v1.7.4.1-59-ge3d3f7d, meaning \"59 commits past the tag v1.7.4.1, at commit ge3d3f7d\" which you can then insert somehow into the right place in your code as you package/build. This is what Git itself does; the result is dumped to a file, whose contents are read into the makefile and then passed into the build via a -D preprocessor option, and placed into various filenames (e.g. the release tarball) directly.\n\nIf you really, really want to do this after every commit, you could, with a post-commit hook, but then only you (and those you give the hook to) will have it, and it's very very possible to get out of sync - you'll also have to have a post-checkout hook, and so on and so on. It's really better for whatever processes that create something needing this version number to get it themselves.\nYou could also use a smudge/clean filter, which would be more like what you actually want (rather than simply after every commit)."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-ls-files - Show information about files in the index and the working tree"
},
{
"role": "assistant",
"content": "OUTPUT git ls-files just outputs the filenames unless --stage is specified in\nwhich case it outputs: [<tag> ]<mode> <object> <stage> <file> git ls-files --eol will show\n\ti/<eolinfo><SPACES>w/<eolinfo><SPACES>attr/<eolattr><SPACE*><TAB><file> git ls-files --unmerged and git ls-files --stage can be used to examine\ndetailed information on unmerged paths. For an unmerged path, instead of recording a single mode/SHA-1 pair,\nthe index records up to three such pairs; one from tree O in stage\n1, A in stage 2, and B in stage 3. This information can be used by\nthe user (or the porcelain) to see what should eventually be recorded at the\npath. (see git-read-tree for more information on state) Without the -z option, pathnames with \"unusual\" characters are\nquoted as explained for the configuration variable core.quotePath (see git-config ). Using -z the filename is output\nverbatim and the line is terminated by a NUL byte. It is possible to print in a custom format by using the --format option, which is able to interpolate different fields using\na %(fieldname) notation. For example, if you only care about the\n\"objectname\" and \"path\" fields, you can execute with a specific\n\"--format\" like git ls-files --format='%(objectname) %(path)'"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Pushing to Git returning Error Code 403 fatal: HTTP request failed\n\nI was able to clone a copy of this repo over HTTPS authenticated. I've made some commits and want to push back out to the GitHub server. Using Cygwin on Windows 7 x64.\nC:\\cygwin\\home\\XPherior\\Code\\lunch_call>git push\nPassword:\nerror: The requested URL returned error: 403 while accessing https://MichaelDrog\n[email protected]/derekerdmann/lunch_call.git/info/refs\n\nfatal: HTTP request failed\n\nAlso set it up with verbose mode. I'm still pretty baffled.\nC:\\cygwin\\home\\XPherior\\Code\\lunch_call>set GIT_CURL_VERBOSE=1\n\nC:\\cygwin\\home\\XPherior\\Code\\lunch_call>git push\nPassword:\n* Couldn't find host github.com in the _netrc file; using defaults\n* About to connect() to github.com port 443 (#0)\n* Trying 207.97.227.239... * 0x23cb740 is at send pipe head!\n* Connected to github.com (207.97.227.239) port 443 (#0)\n* successfully set certificate verify locations:\n* CAfile: C:\\Program Files (x86)\\Git/bin/curl-ca-bundle.crt\n CApath: none\n* SSL connection using AES256-SHA\n* Server certificate:\n* subject: 2.5.4.15=Private Organization; 1.3.6.1.4.1.311.60.2.1.3=US; 1.\n3.6.1.4.1.311.60.2.1.2=California; serialNumber=C3268102; C=US; ST=California; L\n=San Francisco; O=GitHub, Inc.; CN=github.com\n* start date: 2011-05-27 00:00:00 GMT\n* expire date: 2013-07-29 12:00:00 GMT\n* subjectAltName: github.com matched\n* issuer: C=US; O=DigiCert Inc; OU=www.digicert.com; CN=DigiCert High Ass\nurance EV CA-1\n* SSL certificate verify ok.\n> GET /derekerdmann/lunch_call.git/info/refs?service=git-receive-pack HTTP/1.1\nUser-Agent: git/1.7.4.3282.g844cb\nHost: github.com\nAccept: */*\nPragma: no-cache\n\n< HTTP/1.1 401 Authorization Required\n< Server: nginx/1.0.4\n< Date: Thu, 15 Sep 2011 22:44:41 GMT\n< Content-Type: text/plain\n< Connection: keep-alive\n< Content-Length: 55\n< WWW-Authenticate: Basic realm=\"GitHub\"\n<\n* Ignoring the response-body\n* Expire cleared\n* Connection #0 to host github.com left intact\n* Issue another request to this URL: 'https://[email protected]/dereker\ndmann/lunch_call.git/info/refs?service=git-receive-pack'\n* Couldn't find host github.com in the _netrc file; using defaults\n* Re-using existing connection! (#0) with host github.com\n* Connected to github.com (207.97.227.239) port 443 (#0)\n* 0x23cb740 is at send pipe head!\n* Server auth using Basic with user 'MichaelDrogalis'\n> GET /derekerdmann/lunch_call.git/info/refs?service=git-receive-pack HTTP/1.1\nAuthorization: Basic XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX\nUser-Agent: git/1.7.4.3282.g844cb\nHost: github.com\nAccept: */*\nPragma: no-cache\n\n< HTTP/1.1 401 Authorization Required\n< Server: nginx/1.0.4\n< Date: Thu, 15 Sep 2011 22:44:41 GMT\n< Content-Type: text/plain\n< Connection: keep-alive\n< Content-Length: 55\n* Authentication problem. Ignoring this.\n< WWW-Authenticate: Basic realm=\"GitHub\"\n* The requested URL returned error: 401\n* Closing connection #0\n* Couldn't find host github.com in the _netrc file; using defaults\n* About to connect() to github.com port 443 (#0)\n* Trying 207.97.227.239... * 0x23cb740 is at send pipe head!\n* Connected to github.com (207.97.227.239) port 443 (#0)\n* successfully set certificate verify locations:\n* CAfile: C:\\Program Files (x86)\\Git/bin/curl-ca-bundle.crt\n CApath: none\n* SSL re-using session ID\n* SSL connection using AES256-SHA\n* old SSL session ID is stale, removing\n* Server certificate:\n* subject: 2.5.4.15=Private Organization; 1.3.6.1.4.1.311.60.2.1.3=US; 1.\n3.6.1.4.1.311.60.2.1.2=California; serialNumber=C3268102; C=US; ST=California; L\n=San Francisco; O=GitHub, Inc.; CN=github.com\n* start date: 2011-05-27 00:00:00 GMT\n* expire date: 2013-07-29 12:00:00 GMT\n* subjectAltName: github.com matched\n* issuer: C=US; O=DigiCert Inc; OU=www.digicert.com; CN=DigiCert High Ass\nurance EV CA-1\n* SSL certificate verify ok.\n* Server auth using Basic with user 'MichaelDrogalis'\n> GET /derekerdmann/lunch_call.git/info/refs HTTP/1.1\nAuthorization: Basic xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\nUser-Agent: git/1.7.4.3282.g844cb\nHost: github.com\nAccept: */*\nPragma: no-cache\n\n* The requested URL returned error: 403\n* Expire cleared\n* Closing connection #0\nerror: The requested URL returned error: 403 while accessing https://MichaelDrog\n[email protected]/derekerdmann/lunch_call.git/info/refs\n\nfatal: HTTP request failed\n\nThese are the versions of git and curl that I have:\nC:\\Users\\XPherior>git --version\ngit version 1.7.4.msysgit.0\n\nC:\\Users\\XPherior>curl --version\ncurl 7.21.7 (amd64-pc-win32) libcurl/7.21.7 OpenSSL/0.9.8r zlib/1.2.5\nProtocols: dict file ftp ftps gopher http https imap imaps ldap pop3 pop3s rtsp\nsmtp smtps telnet tftp\nFeatures: AsynchDNS GSS-Negotiate Largefile NTLM SSL SSPI libz"
},
{
"role": "assistant",
"content": "I just got the same problem and just figured out what's cause.\nGithub seems only supports ssh way to read&write the repo, although https way also displayed 'Read&Write'.\nSo you need to change your repo config on your PC to ssh way:\n\nEdit .git/config file under your repo directory.\nFind url=entry under section [remote \"origin\"].\nChange it from:\nurl=https://[email protected]/derekerdmann/lunch_call.git\nto:\nurl=ssh://[email protected]/derekerdmann/lunch_call.git\nThat is, change all the texts before @ symbol to ssh://git\nSave config file and quit. now you could use git push origin master to sync your repo on GitHub."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-stash - Stash the changes in a dirty working directory away --pathspec-file-nul"
},
{
"role": "assistant",
"content": "This option is only valid for push command. Only meaningful with --pathspec-from-file . Pathspec elements are\nseparated with NUL character and all other characters are taken\nliterally (including newlines and quotes)."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git - the stupid content tracker GIT_DIFF_PATH_TOTAL"
},
{
"role": "assistant",
"content": "The total number of paths."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Count Git commits per period\n\nis there a way to count the number of commits in certain period (e.g. the last year from 2015-03-01 to 2016-03-01) for git (GitHub) repositories?"
},
{
"role": "assistant",
"content": "To count the commits in a date range in your current branch do this:\n git rev-list --count HEAD --since=\"Dec 3 2015\" --before=\"Jan 3 2016\"\n\nIf you want the count for all branches in one go use --all additionally\ngit rev-list --count --since=\"Dec 3 2015\" --before=\"Jan 3 2016\" --all\n\nif you want to exclude merge-commits, use option --no-merges\ngit rev-list --count --since=\"Dec 3 2015\" --before=\"Jan 3 2016\" --all --no-merges"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git push to multiple repositories simultaneously [duplicate]\nThis question already has answers here:\n \n \n\n\n\n\nHow can I pull/push from multiple remote locations?\n\n (17 answers)\n \n\nClosed 10 years ago.\n\n\n\nHow can I make git push to push not only to origin but also another remote repository?\nas git push is only an alias for git push origin, can I alias git push to push to 2 remote repositories at once (with just that one command)?\nI’m not looking for a non-git script here but would like to set this up for my local repository in git.\nWhen I tried it with post-push scripts I failed."
},
{
"role": "assistant",
"content": "I don't think you can do it just by setting a flag on git, but you can modify a config file that will allow you to push to multiple remote repositories without manually typing them all in (well only typing them in the first time and not after)\nIn the .git/config file you can add multiple urls to a defined remote:\n[remote \"all\"]\n url=ssh://user@server/repos/g0.git\n url=ssh://user@server/repos/g1.git\n\nIf you git push all now you push to all the remote urls."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Github: error cloning my private repository\n\nI'm trying to clone my GitHub project using the https-URL, but it fails with an error:\n$ git clone https://[email protected]/foo/foo-private.git\nCloning into foo-private...\nPassword:\nerror: error setting certificate verify locations:\n CAfile: /bin/curl-ca-bundle.crt\n CApath: none\n while accessing https://[email protected]/foo/foo-private.git/info/refs\n\nfatal: HTTP request failed\n\nWhat am I doing wrong?"
},
{
"role": "assistant",
"content": "I have seen this on Windows, with msysgit 1.7.2.3. You have to fix the path to bin/curl-ca-bundle.crt. I had to specify the absolute path, using back-slashes:\ngit config --system http.sslcainfo \"C:\\Program Files (x86)\\git\\bin\\curl-ca-bundle.crt\"\nThis will result in changes to [git-install-dir]/etc/gitconfig file, which may be edited directly, too.\n(Original solutions found at http://github.com/blog/642-smart-http-support)"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "EGit: Pruning Remote Tracking Branches that have been Deleted on the Remote Repo\nI'm using EGit (for Eclipse) with a team of devs. We have been creating a lot of feature and fix branches for new work, and then merging them into our release branches when they are completed. Right after they are merged into the correct release branch, these temporary branches are usually deleted to keep our remote repo clean. \nI'm noticing that when these branches get deleted, I will fetch from our remote repo, but EGit doesn't remove them from my remote tracking view. My remote tracking view will still show deleted branches that are no longer on the remote repo (and there is no indication that they have been deleted). The only way (I have found) to have my remote tracking view reflect the actual repo is to delete all of my remote tracking branches manually (highlight and delete), and then fetch them again. This seems very roundabout, especially since you can prune remote branches via command line, like this:\ngit remote prune origin\nBasically, what I would like to know is if there is a way to configure/make EGit perform this pruning when remote tracking branches change (after I fetch). Here is my current fetch configuration on my origin remote:"
},
{
"role": "assistant",
"content": "Update March 2014: As mentioned by cheshire's answer, EGit 3.3 added that prune feature.\nYou can see said feature introduced in this Gerrit code review in JGit (and tested here)\nThe entry fetch.prune mentioned in git config can be added to your Egit configuration:\n\n\nOriginal answer (March 2013)\n\nEGit perform this pruning when remote tracking branches change (after I fetch). \n\nNot that I know of.\nMore generally, perform any action after each fetch on the client side is not possible with hooks.\nIt has been requested, and was at one point implemented on the server side only: hook post-upload (run after a fetch), but removed, for security reason in a multi-user environment."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-shortlog - Summarize git log output --until=<date> --before=<date>"
},
{
"role": "assistant",
"content": "Show commits older than a specific date."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-shortlog - Summarize git log output --simplify-merges"
},
{
"role": "assistant",
"content": "Additional option to --full-history to remove some needless\nmerges from the resulting history, as there are no selected\ncommits contributing to this merge."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-log - Show commit logs --[no-]rename-empty"
},
{
"role": "assistant",
"content": "Whether to use empty blobs as rename source."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Finding diff between current and last version\nUsing Git, how can you find the difference between the current and the last version?\ngit diff last version:HEAD"
},
{
"role": "assistant",
"content": "I don't really understand the meaning of \"last version\".\nAs the previous commit can be accessed with HEAD^, I think that you are looking for something like:\ngit diff HEAD^ HEAD\n\nThat also can be applied for a :commithash\ngit diff $commithash^ $commithash\n\nAs of Git 1.8.5, @ is an alias for HEAD, so you can use:\ngit diff @~..@\n\nThe following will also work:\ngit show\n\nIf you want to know the diff between head and any commit you can use:\ngit diff commit_id HEAD\n\nAnd this will launch your visual diff tool (if configured):\ngit difftool HEAD^ HEAD\n\nSince comparison to HEAD is default you can omit it (as pointed out by Orient):\ngit diff @^\ngit diff HEAD^\ngit diff commit_id\n\nWarnings\n\n@ScottF and @Panzercrisis explain in the comments that on Windows the ~ character must be used instead of ^."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Git pulling changes between two local repositories\nI have two clones of same remote repository. I have made some changes to one local repository, how can I pull these changes to the other local repository without pushing it to the remote?"
},
{
"role": "assistant",
"content": "You can treat the second clone the same way you treat a remote respository on another system. You can perform all of the same operations, e.g.\n~/repo1 $ git remote add repo2 ~/repo2\n~/repo1 $ git fetch repo2\n~/repo1 $ git merge repo2/foo"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-worktree - Manage multiple working trees add <path> [<commit-ish>]"
},
{
"role": "assistant",
"content": "Create a worktree at <path> and checkout <commit-ish> into it. The new worktree\nis linked to the current repository, sharing everything except per-worktree\nfiles such as HEAD , index , etc. As a convenience, <commit-ish> may\nbe a bare \" - \", which is synonymous with @{-1} . If <commit-ish> is a branch name (call it <branch> ) and is not found,\nand neither -b nor -B nor --detach are used, but there does\nexist a tracking branch in exactly one remote (call it <remote> )\nwith a matching name, treat as equivalent to: $ git worktree add --track -b <branch> <path> <remote>/<branch> If the branch exists in multiple remotes and one of them is named by\nthe checkout.defaultRemote configuration variable, we’ll use that\none for the purposes of disambiguation, even if the <branch> isn’t\nunique across all remotes. Set it to\ne.g. checkout.defaultRemote=origin to always checkout remote\nbranches from there if <branch> is ambiguous but exists on the origin remote. See also checkout.defaultRemote in git-config . If <commit-ish> is omitted and neither -b nor -B nor --detach used,\nthen, as a convenience, the new worktree is associated with a branch (call\nit <branch> ) named after $(basename <path>) . If <branch> doesn’t\nexist, a new branch based on HEAD is automatically created as if -b <branch> was given. If <branch> does exist, it will be checked out\nin the new worktree, if it’s not checked out anywhere else, otherwise the\ncommand will refuse to create the worktree (unless --force is used). If <commit-ish> is omitted, neither --detach , or --orphan is\nused, and there are no valid local branches (or remote branches if --guess-remote is specified) then, as a convenience, the new worktree is\nassociated with a new unborn branch named <branch> (after $(basename <path>) if neither -b or -B is used) as if --orphan was\npassed to the command. In the event the repository has a remote and --guess-remote is used, but no remote or local branches exist, then the\ncommand fails with a warning reminding the user to fetch from their remote\nfirst (or override by using -f/--force )."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to remove a Gitlab project?\n\nI have created several repositories in GitLab. One of those was for testing purposes and has some commits and branches. I want to delete or remove this repository. How can I do this?"
},
{
"role": "assistant",
"content": "Go to the project page\nSelect \"Settings\"\nSelect the \"General\" section (you must be in the repository you want to delete it)\nIf you have enough rights, then at the bottom of the page will be a button for \"Advanced settings\" (i.e. project settings that may result in data loss) or \"Remove project\" (in newer GitLab versions)\nPush this button and follow the instructions\n\nThis is only available for admins/owner. As a mere project maintainer, you do not see the \"Remove project\" button."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-log - Show commit logs --since=<date> --after=<date>"
},
{
"role": "assistant",
"content": "Show commits more recent than a specific date."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Git remote/shared pre-commit hook\nWith a one official repository as the remote, and multiple local repositories cloned from it, can a pre-commit hook be scripted on that main repository and be enforced on all clones of it?"
},
{
"role": "assistant",
"content": "I don't think so, as hooks are not cloned.\nMay be if that hook script is itself versioned, and then link to (symbolic link) in the clone servers (provided their OS support that link feature).\nOr maybe if the hooks are part of a git template directory used for creating the clones (that would only ensure their presences in the clone repo, that would not guarantee they are actually used and executed).\nBut I don't think there is any \"central\" way to enforce a commit.\n\nAs Jefromi explains even more clearly in the comments (emphasis mine):\n\nI think it really goes against the idea of a git repository to have enforced hooks distributed with the repo.\nMy clone is my repository. I should be able to use git on it however I like, including choosing whether or not to run hooks.\n (And from a security standpoint, that'd be really kind of scary - no one should have the ability to force me to execute certain scripts whenever I run certain git commands.)\n\nI agree with that comment, and have only seen ways to enforce rules applied locally, in a given specialized repo.\nFor instance, you wouldn't push to the central repo directly, but would first push to a QA repo which would accept your commit only if it follows certain rules. If it does, then the QA repo will push your commit to the central repo.\nAnother illustration directly derived from what I just mentioned would be \"Serverless Continuous Integration with Git\", a way to enforce locally private build that works before pushing them anywhere."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-diff - Show changes between commits, commit and working tree, etc --pickaxe-all"
},
{
"role": "assistant",
"content": "When -S or -G finds a change, show all the changes in that\nchangeset, not just the files that contain the change\nin <string>."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Github Pull Requests template not showing\n\nI wanted to create custom Pull Requests template for my Github repo (internal version in my company and not on Github.com), so I followed instructions on this link. I followed below steps:\n\nCreated the new template file in the location: [my-repo]/.github/PULL_REQUEST_TEMPLATE/pull_request_template.md.\nMerged this new file into master.\nCreated a new branch from master, commited some changes into new branch.\nCreated a new Pull Request to master, but the template did not show up.\n\nCreating the new PR did not show up the template I had created. Similar steps for creating new issue templates work fine, but PR templates arent working. I would like to add different templates inside PULL_REQUEST_TEMPLATE folder in order to create multiple pull request templates like feature template, bug-fix template etc. My PR template markdown has the following in it:\n---\nname: Design Review\nabout: Design Review issue template\n\n---\n\n# PR Change Description\nThis PR is to add a new vendor type."
},
{
"role": "assistant",
"content": "You must create templates on the repository's default branch. Templates created in other branches are not available for collaborators to use.\nNOTE: If your PullRequest Template is not applied on every new PR you create it could mostly be due to the following reasons\n\nEither PR template doesn't exist at all in any of the branches.\nOr it is present in non-default branch\n\nYou can store your pull request template in the repository's visible root directory, the docs folder, or the hidden .github directory. Pull request template filenames are not case sensitive, and can have an extension such as .md or .txt."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-log - Show commit logs -P --perl-regexp"
},
{
"role": "assistant",
"content": "Consider the limiting patterns to be Perl-compatible regular\nexpressions. Support for these types of regular expressions is an optional\ncompile-time dependency. If Git wasn’t compiled with support for them\nproviding this option will cause it to die."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How do I get Composer to download the latest commit in the master branch from GitHub for a package?\n\nI am trying to get Composer do download the latest commit for the Behat/MinkSelenium2Driver package. That particular repo only has a master branch. I have tried every method I can think of, including deleting the files and letting it pull them back in, to get it to work but it doesn't.\nHow would I get it to pull in latest committed files or at least those from the commit I list below?\nSpecifically I want to get this commit:\nhttps://github.com/Behat/MinkSelenium2Driver/commit/2e73d8134ec8526b6e742f05c146fec2d5e1b8d6\nThanks,\nPatrick"
},
{
"role": "assistant",
"content": "There is only one way to grab the head of the repository: \n\"require\": { \"behat/mink-selenium2-driver\" : \"dev-master\" }\n\"minimum-stability\": \"dev\"\n\nOh well, at least two ways:\n\"require\": { \"behat/mink-selenium2-driver\" : \"dev-master as 1.1.x-dev\" }\n\"minimum-stability\": \"dev\"\n\nProbably at least three ways:\n\"require\": { \"behat/mink-selenium2-driver\" : \"dev-master#2e73d8134ec8526b6e742f05c146fec2d5e1b8d6\" }\n\"minimum-stability\": \"dev\"\n\nBecause that repository actually aliased the master branch as 1.1.x-dev, this would also work without the minimum-stability affecting all other packages:\n\"require\": { \"behat/mink-selenium2-driver\" : \"1.1.*@dev\" }"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git push gives fatal: unable to update url base from redirection:\n\nI did commit successfully in my local repository. When I try to do:\ngit push https://gitlab.com/priceinsight/jmt4manager/compare/develop...2-retrieve-list-userrecord# 2-retrieve-list-userrecord -v\n\nI got this error:\nPushing to https://gitlab.com/priceinsight/jmt4manager/compare/develop...2-retrieve-list-userrecord#\nfatal: unable to update url base from redirection:\n asked for: https://gitlab.com/priceinsight/jmt4manager/compare/develop...2-retrieve-list-userrecord#/info/refs?service=git-receive-pack\n redirect: https://gitlab.com/users/sign_in"
},
{
"role": "assistant",
"content": "The URL you try to push to is not correct. You are trying to push to the URL https://gitlab.com/priceinsight/jmt4manager/compare/develop...2-retrieve-list-userrecord# which is a webpage that compares two branches and not the URL of a repository. The repository would be https://gitlab.com/priceinsight/jmt4manager."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": ".gitignore not ignoring .idea path\nWhat am I missing that needs to be done in order to get git to ignore my .idea/ path?\nctote@ubuntu:~/dev/1$ git status\nOn branch master\nYour branch is up-to-date with 'origin/master'.\n\nChanges not staged for commit:\n (use \"git add <file>...\" to update what will be committed)\n (use \"git checkout -- <file>...\" to discard changes in working directory)\n\n modified: .idea/.name\n modified: .idea/misc.xml\n modified: .idea/modules.xml\n modified: .idea/vcs.xml\n modified: .idea/workspace.xml\n modified: src/Receiver.java\n modified: test/1/agent/WindowsQueryHandlerTest.java\n\nUntracked files:\n (use \"git add <file>...\" to include in what will be committed)\n\n lib/\n mp1.iml\n\nno changes added to commit (use \"git add\" and/or \"git commit -a\")\n\n\nctote@ubuntu:~/dev/1$ cat .gitignore\n*.class\n\n# Package Files #\n*.war\n*.ear\n\n# IDEA config files\n.idea/"
},
{
"role": "assistant",
"content": ".gitignore only ignores newly added (untracked) files.\nIf you have files that have already been added to the repository, all their changes will be tracked as usual, even if they are matched by .gitignore rules.\nTo remove that folder from the repository (without deleting it from disk), do:\ngit rm --cached -r .idea"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git is very very slow when tracking large binary files\nMy project is six months old and git is very very slow. We track around 30 files which are of size 5 MB to 50 MB. Those are binary files and we keep them in git. I believe those files are making git slow.\nIs there a way to kill all files of size > 5MB from the repository. I know I would lose all of these files and that is okay with me.\nIdeally I would like a command that would list all the big files ( > 5MB) . I can see the list and then I say okay go ahead and delete those files and make git faster.\nI should mention that git is slow not only on my machine but deploying the app on staging environment is now taking around 3 hours. \nSo the fix should be something that will affect the server and not only the users of repository."
},
{
"role": "assistant",
"content": "Do you garbage collect?\ngit gc\n\nThis makes a significant difference in speed, even for small repos."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How do you synchronise projects to GitHub with Android Studio?\n\nI am trying to synchronise a project that I have on in my Android Studio folder to GitHub, but I am not fully sure what to do other than adding my credentials in the options menu. Could someone give me a quick guide, please?"
},
{
"role": "assistant",
"content": "Open the project you want to push in Android Studio.\nClick VCS -> Enable version Control Integration -> Git\nThere doesn't seem to be a way to add a remote through the GUI. So open Git Bash in the root of the project and do git remote add <remote_name> <remote_url>\nNow when you do VCS -> Commit changes -> Commit & Push you should see your remote and everything should work through the GUI.\n\nIf you are getting the error: fatal: remote <remote_name> already exists that means you already added it. To see your remotes do git remote -v and git remote rm <remote_name> to remove.\n\nSee these pages for details:\nhttp://www.jetbrains.com/idea/webhelp/using-git-integration.html\nhttp://gitref.org/remotes/"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-merge - Join two or more development histories together --into-name <branch>"
},
{
"role": "assistant",
"content": "Prepare the default merge message as if merging to the branch <branch> , instead of the name of the real branch to which\nthe merge is made."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-clone - Clone a repository into a new directory -- [ no- ] single-branch"
},
{
"role": "assistant",
"content": "Clone only the history leading to the tip of a single branch,\neither specified by the --branch option or the primary\nbranch remote’s HEAD points at.\nFurther fetches into the resulting repository will only update the\nremote-tracking branch for the branch this option was used for the\ninitial cloning. If the HEAD at the remote did not point at any\nbranch when --single-branch clone was made, no remote-tracking\nbranch is created."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-show - Show various types of objects -U<n> --unified=<n>"
},
{
"role": "assistant",
"content": "Generate diffs with <n> lines of context instead of\nthe usual three.\nImplies --patch ."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-svn - Bidirectional operation between a Subversion repository and Git"
},
{
"role": "assistant",
"content": "SYNOPSIS git svn <command> [<options>] [<arguments>]"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How do I replace a git submodule with another repo?\nHow do I replace a git submodule with a different git repo?\nSpecifically, I have a submodule:\n\nlocated at ./ExternalFrameworks/TestFramework that points to a git repo [email protected]:userA/TestFramework.git \nI'd like it to now point to [email protected]:userB/TestFramework.git.\n\nThe problem is that when I delete the submodule with the method described here, then re-add it using the command \ngit submodule add [email protected]:userB/TestFramework.git\n\nI get this error:\nA git directory for 'ExternalFrameworks/TestFramework' is found locally with remote(s):\n origin [email protected]:userA/TestFramework.git\nIf you want to reuse this local git directory instead of cloning again from\n [email protected]:userB/TestFramework.git\nuse the '--force' option. If the local git directory is not the correct repo\nor you are unsure what this means choose another name with the '--name' option."
},
{
"role": "assistant",
"content": "If the location (URL) of the submodule has changed, then you can simply:\n\nModify the .gitmodules file in the repo root to use the new URL.\nDelete the submodule folder in the repo rm -rf .git/modules/<submodule>.\nDelete the submodule folder in the working directory rm -rf <submodule>.\nRun git submodule sync.\nRun git submodule update.\n\nMore complete info can be found elsewhere:\n\nChanging remote repository for a git submodule"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How do I exit a gitlab pipeline early without failure?\n\nI have a gitlab .gitlab-ci.yml pipeline where the first job makes a decision about whether the rest are executed. Neither choice is a “failure” in the “send email and alert everyone” sense. It simply does or doesn’t need to be done at that time.\nI’m looking for the opposite of allow_failure: true which allows the pipeline to continue regardless of the exit status of the job. Instead, I want determine the continuation status.\nIs there an easy or common way to do this? Or am I, once again, stuck with generating yaml files?"
},
{
"role": "assistant",
"content": "It seems like this is currently not possible to do so in \"easy\" way, see relevant issues:\n\nhttps://gitlab.com/gitlab-org/gitlab/-/issues/16733\nhttps://gitlab.com/gitlab-org/gitlab/-/issues/292816\n\nI personally was going to suggest going DAG route with needs: and artifacts, but i actually liked Elan Ruusamäe approach, using dotenv to pass variables between stages. Here is his example:\n\nthis gave me an idea, that maybe combining dotenv and if\n$SOME_VARIABLE, you could run/skip a job. But it may not work if the\nall the evaluation is performed at pipeline creation time. this\nsnippet is not tested.\nhttps://docs.gitlab.com/ee/ci/variables/#inherit-cicd-variables\n\nbuild:\n stage: build\n script:\n - echo \"SKIP_BUILD=true\" >> .env.skip\n artifacts:\n reports:\n dotenv: .env.skip\n\ndocker build:\n script: echo yadayada\n rules:\n - if: '$SKIP_BUILD != \"true\"'\n\nThis still requires to check for previous status in downstream pipelines and looks pretty hacky, but at least not as hacky as grepping through some text files.\nSince dotenv will likely not work in rules section, previous will have to be converted to something like:\nbuild:\n stage: build\n script:\n - echo \"SKIP_BUILD=true\" >> .env.skip\n artifacts:\n reports:\n dotenv: .env.skip\n\ndocker build:\n script:\n - [ \"$SKIP_BUILD\" = true ] && exit 0\n - your_stuff_here\n dependencies:\n - build\n\n\nSee also: https://docs.gitlab.com/ee/ci/variables/README.html#pass-an-environment-variable-to-another-job"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "\"refusing to merge unrelated histories\" failure while pulling to recovered repository\nI come up with a problem about Git push.\nIt worked successfully before, but it failed this time. In the beginning, I am in my master MINGW64 /d/javasoft/apache-tomcat-7.0.70/webapps/MyNote (master), and then,\n\nI use git remote add origin to relate my remote origin, but it alerts that fatal: remote origin already exists.\nthen, I use git remote rm origin (Someone told me to), and it's OK.\nthen, I use git remote add origin https://github.com/***/***.git again. It's OK.\nthen, I use git push -u origin master ( I tried git push origin master, but I lost my local whole .git for some reason before, so I guess it may be the first time to push, and I should add -u ). BUT, it alerts error: failed to push some refs to 'https://github.com/***/***.git'\nthen, someone told me that I should use git pull origin master before I use push, and I did as it. but, it alerted: fatal: refusing to merge unrelated histories.\nI found some answers in Git refusing to merge unrelated histories on rebase, but it seemed that it didn't work. In my issue, it alerted fatal: Couldn't find remote ref –allow-unrelated-histories\n\n\nHow can I do it? I just want to push..."
},
{
"role": "assistant",
"content": "This cannot be answered shortly.\nWarning: You should not use the --allow-unrelated-histories flag unless you know what unrelated history is and are sure you need it. The check was introduced just to prevent disasters when people merge unrelated projects by mistake.\nAs far as I understand, in your case the following has happened:\nYou have cloned a project at some point 1, and made some development to point 2. Meanwhile, project has evolved to some point 3.\n\nThen you for some reason lost your local .git subdirectory - which contained all your history from 1 to 2. You managed to restore the current state though.\n\nBut now it does not have any history - it looks like the whole project has appeared out of nowhere. If you ask Git to merge them it will not be able to say where your changes are, so it can add them to remote project, as far as I understand it will just report massive add/add conflicts.\nYou should now find back that commit 1 from the remote history where you have cloned the project (I assume you did not pull after that; if you did then you should instead look for the last commit you have pulled). Then you should modify your history so that is starts from that commit 1, and then Git will be able to merge correctly (with pull for example).\nSo, the steps (assuming you are now in your restored commit without history):\n\nestimate where is the commit 1 you have cloned from as some 1?, based on commit time for example\nrun git diff _1?_..HEAD, and read carefully. Make sure that the difference contains only edits which you have made. If it contains more then you should have picked a bit wrong 1? and need to adjust it and repeat this step\nafter you have found the commit 1. You should make it your parent; do git --reset --soft _1_, and then git commit.\n\n\nNow it looks like you have cloned from 1, then made one commit with all your changes. Your intermediate history is lost anyway with your older .git directory, but now you can run your git pull - it will merge correctly."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "gitcli - Git command-line interface and conventions -h"
},
{
"role": "assistant",
"content": "gives a pretty printed usage of the command. $ git describe -h\nusage: git describe [<options>] <commit-ish>*\n or: git describe [<options>] --dirty\n\n --contains find the tag that comes after the commit\n --debug debug search strategy on stderr\n --all use any ref\n --tags use any tag, even unannotated\n --long always use long format\n --abbrev[=<n>] use <n> digits to display SHA-1s Note that some subcommand (e.g. git grep ) may behave differently\nwhen there are things on the command line other than -h , but git\nsubcmd -h without anything else on the command line is meant to\nconsistently give the usage."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How do you change a repository description on GitHub?\n\nWhen you create a repository on GitHub, you can optionally create a description of the repository. Unfortunately, I wrote a description that no longer adequately describes the code in the repo.\nHow do I change the repo description?"
},
{
"role": "assistant",
"content": "They changed the looks slightly, the \"Edit\" button is seen when on the repositories main page, which is the \"Code\" tab. Here is a screencast/animated-screenshot:"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-config - Get and set repository or global options fetch.bundleURI"
},
{
"role": "assistant",
"content": "This value stores a URI for downloading Git object data from a bundle\nURI before performing an incremental fetch from the origin Git server.\nThis is similar to how the --bundle-uri option behaves in git-clone . git clone --bundle-uri will set the fetch.bundleURI value if the supplied bundle URI contains a bundle\nlist that is organized for incremental fetches. If you modify this value and your repository has a fetch.bundleCreationToken value, then remove that fetch.bundleCreationToken value before fetching from\nthe new bundle URI."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-pull - Fetch from and integrate with another repository or a local branch ours"
},
{
"role": "assistant",
"content": "This option forces conflicting hunks to be auto-resolved cleanly by\nfavoring our version. Changes from the other tree that do not\nconflict with our side are reflected in the merge result.\nFor a binary file, the entire contents are taken from our side. This should not be confused with the ours merge strategy, which does not\neven look at what the other tree contains at all. It discards everything\nthe other tree did, declaring our history contains all that happened in it."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to make git mark a deleted and a new file as a file move?\nI've moved a file manually and then I've modified it. According to Git, it is a new file and a removed file. Is there any way to force Git into treating it as a file move?"
},
{
"role": "assistant",
"content": "Git will automatically detect the move/rename if your modification is not too severe.\nJust git add the new file, and git rm the old file.\ngit status will then show whether it has detected the rename.\nadditionally, for moves around directories, you may need to:\n\ncd to the top of that directory structure.\nRun git add -A .\nRun git status to verify that the \"new file\" is now a \"renamed\" file\n\nIf git status still shows \"new file\" and not \"renamed\" you need to follow Hank Gay’s advice and do the move and modify in two separate commits."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-push - Update remote refs along with associated objects -n --dry-run"
},
{
"role": "assistant",
"content": "Do everything except actually send the updates."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.