messages
listlengths 3
3
|
|---|
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How can I rename my branch from TortoiseGit?\nI know the way to rename branch from command line, but - since I'm using TortoiseGit - I'm curious if there are any options to do such thing.\nThanks for the answers :)"
},
{
"role": "assistant",
"content": "In a File Manager, Open your Project root directory (where your .git folder is found).\nRight click and go to:\nTortoiseGit > Switch/Checkout\n\nEnsure the Switch To Option to Branch. Then click the little button to the side of the drop down menu that is denoted by ...\nA window will pop up showing the list of branches for you to choose.\nClick on the one you want to rename.\nHit F2.\nRename your branch. Hit Enter. Click OK.\nNow in the drop down menu, you'll find that the branch-name has been updated."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-cat-file - Provide contents or details of repository objects -z"
},
{
"role": "assistant",
"content": "Only meaningful with --batch , --batch-check , or --batch-command ; input is NUL-delimited instead of\nnewline-delimited. This option is deprecated in favor of -Z as the output can otherwise be ambiguous."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-commit - Record changes to the repository commit.gpgSign"
},
{
"role": "assistant",
"content": "A boolean to specify whether all commits should be GPG signed.\nUse of this option when doing operations such as rebase can\nresult in a large number of commits being signed. It may be\nconvenient to use an agent to avoid typing your GPG passphrase\nseveral times."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-diff - Show changes between commits, commit and working tree, etc git diff"
},
{
"role": "assistant",
"content": "compares the (i)ndex and the (w)ork tree;"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git reset asks 'more?'\nGit windows command line, version 1.8.0\nI have 3 commits so far and when I type\ngit reset --soft HEAD^\n\nnew line comes up with\nMore?\n\nand flashing cursor for input\nThen, whatever I type, I always get \n\nfatal: ambiguous argument 'HEAD\n ': unknown revision or path not in the working tree.\n Use '--' to separate paths from revisions, like this:\n 'git [...] -- [...]\n\nAll other commands works fine in the same folder."
},
{
"role": "assistant",
"content": "see if git log HEAD^ works. If it doesn't, it may be something with your localization or terminal. It seems to be filtering out the ^ symbol. As a workaround, use git reset --soft HEAD~1 for now."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-config - Get and set repository or global options submodule.alternateErrorStrategy"
},
{
"role": "assistant",
"content": "Specifies how to treat errors with the alternates for a submodule\nas computed via submodule.alternateLocation . Possible values are ignore , info , die . Default is die . Note that if set to ignore or info , and if there is an error with the computed alternate, the\nclone proceeds as if no alternate was specified."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-reflog - Manage reflog information --updateref"
},
{
"role": "assistant",
"content": "Update the reference to the value of the top reflog entry (i.e.\n<ref>@{0}) if the previous top entry was pruned. (This\noption is ignored for symbolic references.)"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git - the stupid content tracker gitdiffcore"
},
{
"role": "assistant",
"content": "Tweaking diff output"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-config - Get and set repository or global options never"
},
{
"role": "assistant",
"content": "never show in columns"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to use git commands after enable gitlab's second-factor authentication\n\nToday I've enabled Gitlab's 2nd-factor authentication. After that, since I logged in the Gitlab website, I need to use my cell phone to pass a 6-digits plus my password, that's good, it makes me feel safe.\nHowever, when I use the general operations, for example git clone some-repo.git, I got the error:\nCloning into 'some-repo'...\nremote: HTTP Basic: Access denied\nremote: You must use a personal access token with 'api' scope for Git over HTTP.\nremote: You can generate one at https://gitlab.com/profile/personal_access_tokens\nfatal: Authentication failed for 'some-repo.git'\n\nThen I try existing cloned local repo, using git pull, the same error occurs. Before I enabled the 2nd-factor authentication, all the above operation worked fine.\nFlowing the above error's instructions, I went to the mentioned address: https://gitlab.com/profile/personal_access_tokens. I created the following token, and save the token's key.\n\nHowever, I don't know what to do with this key. Can someone tell me how to use this key to enable the basic operations like git pull, git clone, git push etc...\nEdit\nI had many repos on local before I enabled the 2nd-factor authentication. I want these to work too."
},
{
"role": "assistant",
"content": "As explained in using gitlab token to clone without authentication, you can clone a GitLab repo using your Personal Access Token like this:\ngit clone https://oauth2:[email protected]/yourself/yourproject.git\n\nAs for how to update your existing clones to use the GitLab Personal Access Token, you should edit your .git/config file in each local git directory, which will have an entry something like this:\n[remote \"origin\"]\n url = https://[email protected]/yourself/yourproject.git\n\nChange the url:\n[remote \"origin\"]\n url = https://oauth2:[email protected]/yourself/yourproject.git\n\nNow you can continue using this existing git clone as you did before you enabled 2FA."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Renaming remote git branch\n\nI have 2 git branches: master and experimental.\nExperimental became good, I want to make it the master. I figured I would rename to shuffle things around, but here is what I got:\nnutebook:Stuff nathan$ git remote rename master old\nerror: Could not rename config section 'remote.master' to 'remote.old'\n\nI use GitHub and Git-Tower."
},
{
"role": "assistant",
"content": "The following is a guide to rename your master branch. It will work just as easily to rename your experimental branch.\n\nHere's how I did the renaming.\nFirst, in your working tree, locally rename master to something\n else.\ngit branch -m master old-dev\n\nRenaming a branch does work while you are on the branch, so\n there's no need to checkout something else.\nThen, locally rename the maintenance branch (2.63-branch) to\n master:\ngit branch -m 2.63-branch master\n\nNow, time to mess with the remote. Just in case you screw up, you\n might want to make sure you have a current backup. First, delete the\n remote's master:\ngit push origin :master\n\nAnd now, give the remote your new master:\ngit push origin master:refs/heads/master\n\nUpdate: When creating a new branch, the refs/heads/ prefix is\n needed on the remote side. If the branch already exists (as master did\n above) only the branch name is required on the remote side.\n... and your now-renamed old master:\ngit push origin old-dev:refs/heads/old-dev\n\nFinally, delete the old name of your maintenance branch to prevent\n confusion:\ngit push origin :2.63-branch\n\nClients will now get the 'new' master branch when they pull.\n\nsee this site."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-config - Get and set repository or global options gc.aggressiveDepth"
},
{
"role": "assistant",
"content": "The depth parameter used in the delta compression\nalgorithm used by git gc --aggressive . This defaults\nto 50, which is the default for the --depth option when --aggressive isn’t in use. See the documentation for the --depth option in git-repack for more details."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git - the stupid content tracker git-replace"
},
{
"role": "assistant",
"content": "Create, list, delete refs to replace objects"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Count number of lines in a git repository\nHow would I count the total number of lines present in all the files in a git repository?\ngit ls-files gives me a list of files tracked by git.\nI'm looking for a command to cat all those files. Something like\ngit ls-files | [cat all these files] | wc -l"
},
{
"role": "assistant",
"content": "xargs will let you cat all the files together before passing them to wc, like you asked:\ngit ls-files | xargs cat | wc -l\n\nBut skipping the intermediate cat gives you more information and is probably better:\ngit ls-files | xargs wc -l"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git - the stupid content tracker giteveryday"
},
{
"role": "assistant",
"content": "A useful minimum set of commands for Everyday Git"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to follow only specific issues on Github, instead of watching an entire project? [closed]\n\nClosed. This question is off-topic. It is not currently accepting answers.\n \n \n\n\n\n\n\n\n\n\n\n\n\nWant to improve this question? Update the question so it's on-topic for Stack Overflow.\n\n\nClosed 11 years ago.\n\n\n\n\n\n\n\n Improve this question\n \n\n\n\nIs it possible to follow only specific issues on Github (instead of watching an entire project)? I'd like to get notifications by email when one specific issue changed (pull, state-change, new comments). Is this possible at all?"
},
{
"role": "assistant",
"content": "As per pennstatephil's comment below, there's a SUBSCRIBE on the right pane at the bottom:"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "gitrevisions - Specifying revisions and ranges for Git [<refname>]@{<date>} , e.g. master@{yesterday} , HEAD@{5 minutes ago}"
},
{
"role": "assistant",
"content": "A ref followed by the suffix @ with a date specification\nenclosed in a brace\npair (e.g. {yesterday} , {1 month 2 weeks 3 days 1 hour 1\nsecond ago} or {1979-02-26 18:30:00} ) specifies the value\nof the ref at a prior point in time. This suffix may only be\nused immediately following a ref name and the ref must have an\nexisting log ( $GIT_DIR/logs/<ref> ). Note that this looks up the state\nof your local ref at a given time; e.g., what was in your local master branch last week. If you want to look at commits made during\ncertain times, see --since and --until ."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-help - Display help information about Git"
},
{
"role": "assistant",
"content": "CONFIGURATION VARIABLES help.format If no command-line option is passed, the help.format configuration\nvariable will be checked. The following values are supported for this\nvariable; they make git help behave as their corresponding command-\nline option: \"man\" corresponds to -m|--man , \"info\" corresponds to -i|--info , \"web\" or \"html\" correspond to -w|--web . help.browser, web.browser, and browser.<tool>.path The help.browser , web.browser and browser.<tool>.path will also\nbe checked if the web format is chosen (either by command-line\noption or configuration variable). See -w|--web in the OPTIONS\nsection above and git-web--browse . man.viewer The man.viewer configuration variable will be checked if the man format is chosen. The following values are currently supported: \"man\": use the man program as usual, \"woman\": use emacsclient to launch the \"woman\" mode in emacs\n(this only works starting with emacsclient versions 22), \"konqueror\": use kfmclient to open the man page in a new konqueror\ntab (see Note about konqueror below). Values for other tools can be used if there is a corresponding man.<tool>.cmd configuration entry (see below). Multiple values may be given to the man.viewer configuration\nvariable. Their corresponding programs will be tried in the order\nlisted in the configuration file. For example, this configuration: [man]\n\t\tviewer = konqueror\n\t\tviewer = woman will try to use konqueror first. But this may fail (for example, if\nDISPLAY is not set) and in that case emacs' woman mode will be tried. If everything fails, or if no viewer is configured, the viewer specified\nin the GIT_MAN_VIEWER environment variable will be tried. If that\nfails too, the man program will be tried anyway. man.<tool>.path You can explicitly provide a full path to your preferred man viewer by\nsetting the configuration variable man.<tool>.path . For example, you\ncan configure the absolute path to konqueror by setting man.konqueror.path . Otherwise, git help assumes the tool is\navailable in PATH. man.<tool>.cmd When the man viewer, specified by the man.viewer configuration\nvariables, is not among the supported ones, then the corresponding man.<tool>.cmd configuration variable will be looked up. If this\nvariable exists then the specified tool will be treated as a custom\ncommand and a shell eval will be used to run the command with the man\npage passed as arguments. Note about konqueror When konqueror is specified in the man.viewer configuration\nvariable, we launch kfmclient to try to open the man page on an\nalready opened konqueror in a new tab if possible. For consistency, we also try such a trick if man.konqueror.path is\nset to something like A_PATH_TO/konqueror . That means we will try to\nlaunch A_PATH_TO/kfmclient instead. If you really want to use konqueror , then you can use something like\nthe following: [man]\n\t\tviewer = konq\n\n\t[man \"konq\"]\n\t\tcmd = A_PATH_TO/konqueror Note about git config --global Note that all these configuration variables should probably be set\nusing the --global flag, for example like this: $ git config --global help.format web\n$ git config --global web.browser firefox as they are probably more user specific than repository specific.\nSee git-config for more information about this."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to create the branch from a specific commit in a different branch\nI have made several commits in the master branch and then merged them to the dev branch.\nI want to create a branch from a specific commit in the dev branch, which was first committed in the master branch.\nI used the commands:\ngit checkout dev\ngit branch <branch name> <commit id>\n\nHowever, this creates the branch from the master branch, not the dev branch I expected. The commit id is same in the master branch and dev branch.\nSo, how can I distinguish same commit id in a different branch?\nPS: I made an example at GitHub.\nI used the commands:\ngit checkout dev\ngit branch test 07aeec983bfc17c25f0b0a7c1d47da8e35df7af8\n\nI expect that the test branch contains aa.txt, bb.txt, and cc.txt. However, the test branch only contains aa.txt and cc.txt. It most likely created the branch from the master branch."
},
{
"role": "assistant",
"content": "If you are using this form of the branch command (with start point), it does not matter where your HEAD is.\nWhat you are doing:\ngit checkout dev\ngit branch test 07aeec983bfc17c25f0b0a7c1d47da8e35df7af8\n\n\nFirst, you set your HEAD to the branch dev,\nSecond, you start a new branch on commit 07aeec98. There is no bb.txt at this commit (according to your github repo).\n\nIf you want to start a new branch at the location you have just checked out, you can either run branch with no start point:\ngit branch test\n\nor as other have answered, branch and checkout there in one operation:\ngit checkout -b test\n\n\nI think that you might be confused by that fact that 07aeec98 is part of the branch dev. It is true that this commit is an ancestor of dev, its changes are needed to reach the latest commit in dev. However, they are other commits that are needed to reach the latest dev, and these are not necessarily in the history of 07aeec98.\n8480e8ae (where you added bb.txt) is for example not in the history of 07aeec98. If you branch from 07aeec98, you won't get the changes introduced by 8480e8ae.\nIn other words: if you merge branch A and branch B into branch C, then create a new branch on a commit of A, you won't get the changes introduced in B.\nSame here, you had two parallel branches master and dev, which you merged in dev. Branching out from a commit of master (older than the merge) won't provide you with the changes of dev.\n\nIf you want to permanently integrate new changes from master into your feature branches, you should merge master into them and go on. This will create merge commits in your feature branches, though.\nIf you have not published your feature branches, you can also rebase them on the updated master: git rebase master featureA. Be prepared to solve possible conflicts.\nIf you want a workflow where you can work on feature branches free of merge commits and still integrate with newer changes in master, I recommend the following:\n\nbase every new feature branch on a commit of master\ncreate a dev branch on a commit of master\nwhen you need to see how your feature branch integrates with new changes in master, merge both master and the feature branch into dev.\n\nDo not commit into dev directly, use it only for merging other branches.\nFor example, if you are working on feature A and B:\na---b---c---d---e---f---g -master\n \\ \\\n \\ \\-x -featureB\n \\\n \\-j---k -featureA\n\nMerge branches into a dev branch to check if they work well with the new master:\na---b---c---d---e---f---g -master\n \\ \\ \\\n \\ \\ \\--x'---k' -dev\n \\ \\ / / \n \\ \\-x---------- / -featureB\n \\ /\n \\-j---k--------------- -featureA\n\nYou can continue working on your feature branches, and keep merging in new changes from both master and feature branches into dev regularly.\na---b---c---d---e---f---g---h---i----- -master\n \\ \\ \\ \\\n \\ \\ \\--x'---k'---i'---l' -dev\n \\ \\ / / /\n \\ \\-x---------- / / -featureB\n \\ / / \n \\-j---k-----------------l------ -featureA\n\nWhen it is time to integrate the new features, merge the feature branches (not dev!) into master."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-format-patch - Prepare patches for e-mail submission <limit>"
},
{
"role": "assistant",
"content": "An integer parameter specifies a cut-off percent (3% by default).\nDirectories contributing less than this percentage of the changes\nare not shown in the output."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How can I debug git/git-shell related problems?\nHow can I have some debug information regarding git/git-shell? \nI had a problem, that user1 could clone a repository without problem, while user2 could clone only an empty one. I had set GIT_TRACE=1, but nothing useful was told.\nFinally, after a long trial and error, it turned out that it was a permission problem on a file. An appropriate error message could short-circuit this problem."
},
{
"role": "assistant",
"content": "For even more verbose output use following:\nGIT_CURL_VERBOSE=1 GIT_TRACE=1 git pull origin master"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How do I clone into a non-empty directory?\nI have directory A with files matching directory B. Directory A may have other needed files. Directory B is a git repo.\nI want to clone directory B to directory A but git-clone won't allow me to since the directory is non-empty.\nI was hoping it would just clone .git and since all the files match I could go from there?\nI can't clone into an empty directory because I have files in directory A that are not in directory B and I want to keep them.\nCopying .git is not an option since I want refs to push/pull with and I don't want to set them up manually.\nIs there any way to do this?\nUpdate: I think this works, can anyone see any problems? -->\ncd a\ngit clone --no-hardlinks --no-checkout ../b a.tmp \nmv a.tmp/.git .\nrm -rf a.tmp\ngit unstage # apparently git thinks all the files are deleted if you don't do this"
},
{
"role": "assistant",
"content": "This worked for me:\ngit init\ngit remote add origin PATH/TO/REPO\ngit fetch\ngit reset origin/master # Required when the versioned files existed in path before \"git init\" of this repo.\ngit checkout -t origin/master\n\nNOTE: -t will set the upstream branch for you, if that is what you want, and it usually is."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-diff-index - Compare a tree to the working tree or index <limit>"
},
{
"role": "assistant",
"content": "An integer parameter specifies a cut-off percent (3% by default).\nDirectories contributing less than this percentage of the changes\nare not shown in the output."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to avoid merge-commit hell on GitHub/BitBucket\nWe're ending up with a lot of commits like this in our repo:\nMerge branch 'master' of bitbucket.org:user/repo\n\nThis happens every time a developer syncs his/hers local fork to the top-level repo.\nIs there anyway to avoid this merge-commit hell from cluttering all the repo log? Can one avoid them when initiating the pull-requests in some way?\nI know I can do git rebase if this is done in my local VM only, is there any equivalence in the GitHub/BitBucket UI?\nHow do you guys do it?"
},
{
"role": "assistant",
"content": "Rebase Feature Branches Before Merging\nIf you want to avoid merge commits, you need to ensure all commits are fast-forwards. You do this by making sure your feature branch rebases cleanly onto your line of development before a merge like so:\ngit checkout master\ngit checkout -b feature/foo\n\n# make some commits\n\ngit rebase master\ngit checkout master\ngit merge --ff-only feature/foo\n\nRebase also has a lot of flags, including interactive rebasing with the -i flag, but you may not need that if you're keeping things as simple as possible and want to preserve all of your branch history on a merge.\nUse the --ff-only Flag\nAside from rebasing, the use of the --ff-only flag will ensure that only fast-forward commits are allowed. A commit will not be made if it would be a merge commit instead. The git-merge(1) manual page says:\n\n--ff-only \nRefuse to merge and exit with a non-zero status unless the current\n HEAD is already up-to-date or the merge can be resolved as a\n fast-forward."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Gitlab key format issue\n\nI am facing a strange situation where I am using gitlab account to handle my code. I am using ssh protocol to access the repo. I am able to pull the code but I am receiving the following error while I try to push the code. This could be something silly on my side. But I have the keys stored in my gitlab profile and able to use it to pull the code.\nError :\n$ git push origin master\nkey_load_public: invalid format\nEnter passphrase for key '/c/Users/username/.ssh/id_rsa':\nAccess denied.\nfatal: Could not read from remote repository.\n\nPlease make sure you have the correct access rights\nand the repository exists."
},
{
"role": "assistant",
"content": "Finally I have been able to resolve this issue and I am posting it for other users. If the keys generated by putty is not helping you to access the gitlab repo, try generating the keys from gitbash terminal using the command ssh-keygen and save the files in .ssh folder of your user account.\nThe linux style key generation made my life easy as I was trying to generate key in windows environment with putty keygen.\nHope this helps somebody."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-fast-import - Backend for fast Git data importers"
},
{
"role": "assistant",
"content": "TIPS AND TRICKS The following tips and tricks have been collected from various\nusers of fast-import, and are offered here as suggestions. Use One Mark Per Commit When doing a repository conversion, use a unique mark per commit\n( mark :<n> ) and supply the --export-marks option on the command\nline. fast-import will dump a file which lists every mark and the Git\nobject SHA-1 that corresponds to it. If the frontend can tie\nthe marks back to the source repository, it is easy to verify the\naccuracy and completeness of the import by comparing each Git\ncommit to the corresponding source revision. Coming from a system such as Perforce or Subversion, this should be\nquite simple, as the fast-import mark can also be the Perforce changeset\nnumber or the Subversion revision number. Freely Skip Around Branches Don’t bother trying to optimize the frontend to stick to one branch\nat a time during an import. Although doing so might be slightly\nfaster for fast-import, it tends to increase the complexity of the frontend\ncode considerably. The branch LRU builtin to fast-import tends to behave very well, and the\ncost of activating an inactive branch is so low that bouncing around\nbetween branches has virtually no impact on import performance. Handling Renames When importing a renamed file or directory, simply delete the old\nname(s) and modify the new name(s) during the corresponding commit.\nGit performs rename detection after-the-fact, rather than explicitly\nduring a commit. Use Tag Fixup Branches Some other SCM systems let the user create a tag from multiple\nfiles which are not from the same commit/changeset. Or to create\ntags which are a subset of the files available in the repository. Importing these tags as-is in Git is impossible without making at\nleast one commit which “fixes up” the files to match the content\nof the tag. Use fast-import’s reset command to reset a dummy branch\noutside of your normal branch space to the base commit for the tag,\nthen commit one or more file fixup commits, and finally tag the\ndummy branch. For example since all normal branches are stored under refs/heads/ name the tag fixup branch TAG_FIXUP . This way it is impossible for\nthe fixup branch used by the importer to have namespace conflicts\nwith real branches imported from the source (the name TAG_FIXUP is not refs/heads/TAG_FIXUP ). When committing fixups, consider using merge to connect the\ncommit(s) which are supplying file revisions to the fixup branch.\nDoing so will allow tools such as git blame to track\nthrough the real commit history and properly annotate the source\nfiles. After fast-import terminates the frontend will need to do rm .git/TAG_FIXUP to remove the dummy branch. Import Now, Repack Later As soon as fast-import completes the Git repository is completely valid\nand ready for use. Typically this takes only a very short time,\neven for considerably large projects (100,000+ commits). However repacking the repository is necessary to improve data\nlocality and access performance. It can also take hours on extremely\nlarge projects (especially if -f and a large --window parameter is\nused). Since repacking is safe to run alongside readers and writers,\nrun the repack in the background and let it finish when it finishes.\nThere is no reason to wait to explore your new Git project! If you choose to wait for the repack, don’t try to run benchmarks\nor performance tests until repacking is completed. fast-import outputs\nsuboptimal packfiles that are simply never seen in real use\nsituations. Repacking Historical Data If you are repacking very old imported data (e.g. older than the\nlast year), consider expending some extra CPU time and supplying\n--window=50 (or higher) when you run git repack .\nThis will take longer, but will also produce a smaller packfile.\nYou only need to expend the effort once, and everyone using your\nproject will benefit from the smaller repository. Include Some Progress Messages Every once in a while have your frontend emit a progress message\nto fast-import. The contents of the messages are entirely free-form,\nso one suggestion would be to output the current month and year\neach time the current commit date moves into the next month.\nYour users will feel better knowing how much of the data stream\nhas been processed."
}
] |
[
{
"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 --directory"
},
{
"role": "assistant",
"content": "If a whole directory is classified as \"other\", show just its\nname (with a trailing slash) and not its whole contents.\nHas no effect without -o/--others."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Do git tags get pushed as well?\nSince I created my repository it appears that the tags I have been\ncreating are not pushed to the repository. When I do git tag on the\nlocal directory all the tags are present, but when I logon to the\nremote repository and do a git tag, only the first few show up.\nWhat could the problem be?."
},
{
"role": "assistant",
"content": "You could do this:\ngit push --tags"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-log - Show commit logs --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": "How to fix 'The project you were looking for could not be found' when using git clone\nI am trying to clone a project from gitlab to my local machine. I have been granted rights as a developer, and use the command 'git clone \n\nNone of the protocols work (ssh and https neither work)\n\nThe error message I am getting:\nremote: The project you were looking for could not be found.\nfatal: repository 'https://gitlab.com/KZA_Connected/skilltree.git/' not found\n\nAny help would be highly appreciated."
},
{
"role": "assistant",
"content": "I solved this by simply adding username to url like below, \nbefore:\nhttps://gitlab.com/gitlab_user/myrepo.git\nafter:\nhttps://[email protected]/gitlab_user/myrepo.git"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-rev-list - Lists commit objects in reverse chronological order %cr"
},
{
"role": "assistant",
"content": "committer date, relative"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Git .gitignore to ignore only folder in root directory\nHere is my .gitignore\nstatic/\n\nand I have installed git on the folder named project there is a folder named static and another folder called app and inside the app folder, there is another folder static. The above .gitignore ignore both static folders, That is not what I want.\nWhat I want is to ignore the folder project/static/ not the folder project/app/static/ How can I do that?"
},
{
"role": "assistant",
"content": "Just add / before static/, should be like\n /static/\n\n# ^ forward slash before the folder name signifies root dir"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-clone - Clone a repository into a new directory <directory>"
},
{
"role": "assistant",
"content": "The name of a new directory to clone into. The \"humanish\"\npart of the source repository is used if no <directory> is\nexplicitly given ( repo for /path/to/repo.git and foo for host.xz:foo/.git ). Cloning into an existing directory\nis only allowed if the directory is empty."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Deriving maven artifact version from git branch\nWe have a workflow requirement that essentially mean that we need to have the artifact version of a module externally defined from the current branch in git.\nI.e. if we are on the master branch in git, I need <version>master-...</version> and if we are on the bugfixX branch, I need <version>bugfixX-....</version> for the generated artifact for this pom.xml.\nI have previously found that https://github.com/koraktor/mavanagaiata can provide the SHA-1 hash as a property and it appears from the documentation that it can also provide the branch, so perhaps if it could be run early enough in the process we could set the property and just put <version>${our.version}</version> in the pom. If this is possible, I would very much like to see a working pom.xml (and reward a 500 point bounty for it too).\nIf not, I guess we are into either preprocessing or \"git checkout\" do extra magic with some of the hooks (which I have not yet tried, working code would be great too).\nWe have a top level pom, which can be run to generate a property file in \"..\" before building the modules where this functionality I'm asking about needs to go.\nAny suggestions on how to solve this?"
},
{
"role": "assistant",
"content": "Update 2022: Alternative solutions were brought into existence since this answer was written 2012. While the Git-hook-based solution presented here still holds (with its pros and cons), some good answers here present plugin-based or even pure Maven solutions which I recommend to consider.\n\nIndeed, [note 2022: unless some plugins are added to the project], Maven can't change the version of it's own project in one run with other goals. On top of it, raw Maven doesn't support arbitrary properties in the <version> tag. Therefore, a separate execution is required to run a goal which will change the version of the POM. There are various plugins which can do it. For example: versions:set goal from versions plugin - http://mojo.codehaus.org/versions-maven-plugin/set-mojo.html\nSo, you might execute it as follows:\nmvn versions:set -DgenerateBackupPoms=false -DnewVersion=$branch-SNAPSHOT\n\nwhere the $branch variable has to contain current Git branch name; it can be extracted with git rev-parse, like this:\nbranch=$(git rev-parse --abbrev-ref HEAD)\n\nBut still, one needs to execute it somehow. You can do manually, but it is cumbersome. So, my guess is that indeed the most robust solution would be to approach this from Git side. That is - a Git hook. Here is the complete Git post-checkout hook which will do the job (same code as above with some filtering to run the hook only when the branch is checked out, not the individual files only):\n#!/bin/bash\n\necho 'Will change the version in pom.xml files...'\n\n# check if the checkout was to checkout a branch\nif [ $3 != '1' ]\n then echo 'git checkout did not checkout a branch - quitting';exit\nfi\n\n# get current branch name\nbranch=$(git rev-parse --abbrev-ref HEAD)\nversion=$branch-SNAPSHOT\n\n# run maven versions plugin to set new version\nmvn versions:set -DgenerateBackupPoms=false -DnewVersion=$version\n\necho 'Changed version in pom.xml files to $version'\n\nPut this content to the file PROJECTDIR\\.git\\hooks\\post-checkout file. Note that the hook file should be executable to run it (chmod +x post-checkout).\nFew notes about versions plugin - it is pretty flexible and supports many options and have few other goals which might be of help, depending on your project structure (do you use parent poms or not, do childs have their own versions or do they derive from parent, etc.). So, the hook above might be modified slightly to support you specific case by using other goals from versions plugin or by specifying additional parameters.\nPros:\n\nRobust\nNo need to change anything in the pom.xml files themselves to make this work\nThis \"functionality\" can be turned off simply by deactivating the hook (remove or make not executable) - again, no changes are required in the pom.xml\n\nCons:\n\nOne can't enforce others to use a hook - it should be installed manually after the repo is cloned (or, you can provide a script to install the hook if supposed Git users are afraid of touching the stuff inside .git directory).\n\n\nMore elaborate version of the Bash script for the Git hook:\nHereafter is the more complicated version of the hook, which will not only set the version to the branch name, but will also preserve the suffix of the old version. For example, provided old version master-1.0-SNAPSHOT, switching to feature1 branch will change the version of the project to feature1-1.0-SNAPSHOT. This bash script suffers from few problems (requires branch names without dash symbol (-) in the name, and only takes the version of the root pom), but may give an idea of how the hook may be extended: given a mix of mvn and bash commands you can extract and update quite a lot of the information in the POM.\n#!/bin/bash\n\necho 'Will change the version in pom.xml files...'\n\n# check if the checkout was to checkout a branch\nif [ $3 != '1' ]\n then echo 'git checkout did not checkout a branch - quitting';exit\nfi\n\n# get current branch name\nbranch=$(git rev-parse --abbrev-ref HEAD)\n\n# get current version of the top level pom\ncurrent_version=$(mvn help:evaluate -Dexpression=project.version | grep -v '\\[.*')\n\n# extract version suffix\nsuffix=$(echo $current_version | cut -d \\- -f 2)\n\n# build new version\nversion=$branch-$suffix\n\n# run maven versions plugin to set new version\nmvn versions:set -DgenerateBackupPoms=false -DnewVersion=$version\n\necho 'Changed version in pom.xml files to $version'"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How can I revert multiple Git commits (already pushed) to a published repository?\nNew to git, and already messing up.\nI've commited and pushed some changes to a remote dev machine.\nI need to recover an older version, but keep the \"bad progress\" doing so far to keep working on a separate branch;\nI was thinking doing it like this:\n\nCreate a local branch named: \"tested-thing\"\nRevert local repository to the state where it worked (hopefully meaningful commits will help);\nPush to remote\nfinish tests on tested-thing \nMerge \"tested-thing\" into dev\nPush to remote\n\nBetween steps 3 and 5 other developers may commit and push, and I'm afraid this may result on a \"merge tragedy\" - Anyway, may this be a proper way to go ?\nUPDATE:\nThe main problem here resides on 2)\nHere, on topic: \"breaking work into a topic branch\"\nhttp://learn.github.com/p/undoing.html\nThey suggest:\n\n$ git branch test\n$ git reset --hard a6b4c974\n\nBy doing so, other developers could still:\n$ git commit (on the dev branch)\nand I can checkout to test and work it out until merge time.\nDespite all your options, this feels like to be a nice approach to follow. \nHowever, it's not stated if this can be done after we have pushed ?\nPlease note the following: Since I made those changes and I mess up the all thing, no one else have worked on the repository so far. So, if I revert the working directory, no one will notice."
},
{
"role": "assistant",
"content": "The Problem\nThere are a number of work-flows you can use. The main point is not to break history in a published branch unless you've communicated with everyone who might consume the branch and are willing to do surgery on everyone's clones. It's best not to do that if you can avoid it.\nSolutions for Published Branches\nYour outlined steps have merit. If you need the dev branch to be stable right away, do it that way. You have a number of tools for Debugging with Git that will help you find the right branch point, and then you can revert all the commits between your last stable commit and HEAD.\nEither revert commits one at a time, in reverse order, or use the <first_bad_commit>..<last_bad_commit> range. Hashes are the simplest way to specify the commit range, but there are other notations. For example, if you've pushed 5 bad commits, you could revert them with:\n# Revert a series using ancestor notation.\ngit revert --no-edit dev~5..dev\n\n# Revert a series using commit hashes.\ngit revert --no-edit ffffffff..12345678\n\nThis will apply reversed patches to your working directory in sequence, working backwards towards your known-good commit. With the --no-edit flag, the changes to your working directory will be automatically committed after each reversed patch is applied.\nSee man 1 git-revert for more options, and man 7 gitrevisions for different ways to specify the commits to be reverted.\nAlternatively, you can branch off your HEAD, fix things the way they need to be, and re-merge. Your build will be broken in the meantime, but this may make sense in some situations.\nThe Danger Zone\nOf course, if you're absolutely sure that no one has pulled from the repository since your bad pushes, and if the remote is a bare repository, then you can do a non-fast-forward commit.\ngit reset --hard <last_good_commit>\ngit push --force\n\nThis will leave the reflog intact on your system and the upstream host, but your bad commits will disappear from the directly-accessible history and won't propagate on pulls. Your old changes will hang around until the repositories are pruned, but only Git ninjas will be able to see or recover the commits you made by mistake."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-config - Get and set repository or global options log.mailmap"
},
{
"role": "assistant",
"content": "If true, makes git-log , git-show , and git-whatchanged assume --use-mailmap , otherwise\nassume --no-use-mailmap . True by default."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "pre-commit/hook: No such file or directory\nI get this error when I try to commit.\nOS - Latest OSX\nGit version - git version 2.11.0 (Apple Git-81)\n.git/hooks/pre-commit: line 2: ./node_modules/pre-commit/hook: No such file or directory"
},
{
"role": "assistant",
"content": "pre-commit hook runs first when you try to commit changes, it can be used to do certain checks, tests, conditions. In this case, clearly, you don't have it, that's why it's complaining.\nGo to .git/hooks directory and remove pre-commit file, as its trying to reference to node_modules/pre-commit/hook. It should resolve it. \nOther option is append your commit with option: --no-verify, it will make the commit without checking."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to delete files in github using the web interface\n\nThe title pretty much is the question. I am aware of git rm file but this isn't what I am looking for. I am looking for a way to delete files and folders in a github repo using ONLY a browser."
},
{
"role": "assistant",
"content": "This is not (yet?) available through the web interface.\nAs GitHub added File editing, then File creation features, this may make sense to propose such a feature. The recommended channel to do so is to send an email to [email protected].\nUpdate\nDeletion of files through the web interface is now available."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-shortlog - Summarize git log output --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-config - Get and set repository or global options push.recurseSubmodules"
},
{
"role": "assistant",
"content": "May be \"check\", \"on-demand\", \"only\", or \"no\", with the same behavior\nas that of \"push --recurse-submodules\".\nIf not set, no is used by default, unless submodule.recurse is\nset (in which case a true value means on-demand )."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to convert a readonly git clone from github to a forked one\n\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 - the stupid content tracker <file>"
},
{
"role": "assistant",
"content": "Indicates a filename - almost always relative to the\nroot of the tree structure GIT_INDEX_FILE describes."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git - the stupid content tracker git-upload-archive"
},
{
"role": "assistant",
"content": "Send archive back to git-archive"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-config - Get and set repository or global options core.sharedRepository"
},
{
"role": "assistant",
"content": "When group (or true ), the repository is made shareable between\nseveral users in a group (making sure all the files and objects are\ngroup-writable). When all (or world or everybody ), the\nrepository will be readable by all users, additionally to being\ngroup-shareable. When umask (or false ), Git will use permissions\nreported by umask(2). When 0xxx , where 0xxx is an octal number,\nfiles in the repository will have this mode value. 0xxx will override\nuser’s umask value (whereas the other options will only override\nrequested parts of the user’s umask value). Examples: 0660 will make\nthe repo read/write-able for the owner and group, but inaccessible to\nothers (equivalent to group unless umask is e.g. 0022 ). 0640 is a\nrepository that is group-readable but not group-writable.\nSee git-init . False by default."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Git merge doesn't use default merge message, opens editor with default message\nHow can I force git merge to use the default merge message instead of loading my editor with said message?\nI have no editor listed in git config -l, so I'm not sure why it opens an editor."
},
{
"role": "assistant",
"content": "Found the answer after some digging\nEDIT: As per Mark's suggestion, this is the best way to do so: \ngit config --global core.mergeoptions --no-edit"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to update my working Git branch from another branch (develop)?\n\nI made a new branch called feature1 from the main develop branch a month ago.\n⇒ git branch \n develop\n* feature1\n\nI've been working on feature1 for a month now and a lot of changes have been pushed to develop.\nHow can I update my current branch feature1 with the latest commits from develop?\nI DO NOT want to checkout master and merge my feature1 branch into it. Neither do I want to use git cherry-pick to manually move commits from develop to feature1.\nHow would I go about doing this?"
},
{
"role": "assistant",
"content": "You just merge develop to feature1:\ngit checkout feature1\ngit merge develop\n\nThere is no need to involve another branch such as master."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "On GitHub, can I fork just a wiki?\n\nIf I fork repository joe/foo, and it has a Wiki, I won't get the wiki. Right now I'm just interested in forking the wiki to add pages to it.\n\nIs that possible without forking the repository?\nIf not, is it possible at all?"
},
{
"role": "assistant",
"content": "In June 2019, here's how I did that:\n\nFork a repo. The wiki is not forked automatically. So your fork will have empty wiki.\nCreate a wiki in the forked repo. Just create an empty Home page or whatever.\nClone the git repo of original wiki: git clone https://github.com/org-a/project-x.wiki.git\nAssuming your forked repo now sits in https://github.com/org-b/project-x, add the new remote to the wiki repo: git remote add fork https://github.com/org-b/project-x.wiki.git\nDo the force push to overwrite your wiki with the original git push -f fork master\n\nGreat. Now you have forked a repo and its wiki.\n(By the way, Github should do this automatically, right?)"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "cannot pull Git remote repository from Sourcetree\n\nI Generated ssh keys and configured my git and SourceTree. I could git pull and do other operations from Git-bash. \nNote: I have added the following in .bashrc to make it work.\neval `ssh-agent`\nssh-add\n\nHowever, when I try to git pull in SourceTree, I get this.\n\ngit -c diff.mnemonicprefix=false -c core.quotepath=false fetch origin\n Permission denied (publickey,password). fatal: Could not read from\n remote repository.\nPlease make sure you have the correct access rights and the repository\n exists.\n\nWhen I tried to create ssh-key from Putty(windows), it goes further, but waits with this following message!\n\ngit -c diff.mnemonicprefix=false -c core.quotepath=false fetch origin\n The server's host key is not cached in the registry. You have no\n guarantee that the server is the computer you think it is. The\n server's rsa2 key fingerprint is:\nssh-rsa 2048 0f:ee:bb:1c:6c:b4:50:0e:54:d6:e9:55:9b:38:45:df If you\n trust this host, enter \"y\" to add the key to PuTTY's cache and carry\n on connecting. If you want to carry on connecting just once, without\n adding the key to the cache, enter \"n\". If you do not trust this host,\n press Return to abandon the connection.\n\nif I open the terminal in SourceTree(which is git-bash), it asks me for passphrase. So, i suspect my .bashrc is not sourced by SourceTree. Or am I missing something else?"
},
{
"role": "assistant",
"content": "I changed the client configuration from putty to openssh.\nGo to: Menu Tools > Options > SSH Client"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-config - Get and set repository or global options remote.<name>.prune"
},
{
"role": "assistant",
"content": "When set to true, fetching from this remote by default will also\nremove any remote-tracking references that no longer exist on the\nremote (as if the --prune option was given on the command line).\nOverrides fetch.prune settings, if any."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git - the stupid content tracker git-credential-cache"
},
{
"role": "assistant",
"content": "Helper to temporarily store passwords in memory"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-mergetool - Run merge conflict resolution tools to resolve merge conflicts"
},
{
"role": "assistant",
"content": "DESCRIPTION Use git mergetool to run one of several merge utilities to resolve\nmerge conflicts. It is typically run after git merge . If one or more <file> parameters are given, the merge tool program will\nbe run to resolve differences in each file (skipping those without\nconflicts). Specifying a directory will include all unresolved files in\nthat path. If no <file> names are specified, git mergetool will run\nthe merge tool program on every file with merge conflicts."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git - the stupid content tracker GIT_COMMITTER_DATE"
},
{
"role": "assistant",
"content": "The date used for the committer identity when creating commit or tag objects, or\nwhen writing reflogs. See git-commit for valid formats."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-init - Create an empty Git repository or reinitialize an existing one --shared [ = ( false | true | umask | group | all | world | everybody | <perm> )]"
},
{
"role": "assistant",
"content": "Specify that the Git repository is to be shared amongst several users. This\nallows users belonging to the same group to push into that\nrepository. When specified, the config variable core.sharedRepository is\nset so that files and directories under $GIT_DIR are created with the\nrequested permissions. When not specified, Git will use permissions reported\nby umask (2). The option can have the following values, defaulting to group if no value\nis given: umask false Use permissions reported by umask (2). The default, when --shared is not\nspecified. group true Make the repository group-writable, (and g+sx , since the git group may not be\nthe primary group of all users). This is used to loosen the permissions of an\notherwise safe umask (2) value. Note that the umask still applies to the other\npermission bits (e.g. if umask is 0022 , using group will not remove read\nprivileges from other (non-group) users). See 0xxx for how to exactly specify\nthe repository permissions. all world everybody Same as group , but make the repository readable by all users. <perm> <perm> is a 3-digit octal number prefixed with 0 and each file\nwill have mode <perm> . <perm> will override users' umask (2)\nvalue (and not only loosen permissions as group and all do). 0640 will create a repository which is group-readable, but\nnot group-writable or accessible to others. 0660 will create a repo\nthat is readable and writable to the current user and group, but\ninaccessible to others (directories and executable files get their x bit from the r bit for corresponding classes of users)."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "What constitutes a merge conflict in Git?\nHow does git determine that a particular merge has a conflict and what the conflict is?\nMy guess would go something like this: if the two commits being merged have a common parent commit, and if they have both changed line X from what the parent had, that's a conflict.\nWhat complicates my understanding is:\n\n\"Changing line X\" can mean replacing it with several new lines, and that's still shown as one conflict (version A has this one line, and version B has these 5 lines, or whatever)\nIf you did insert lines in one of the commits, a dumber algorithm would think that all subsequent lines had changed: Line 30 now has the former contents of line 25, 31 has the former contents of 26, etc. But git can tell that those are the same, and I don't know how.\n\nCan anybody explain how this works, or point me to a link that does?"
},
{
"role": "assistant",
"content": "Basically, with git, every merge is a conflict, which leaves you with an index that contains three versions of each file, the versions from each branch and the base. On this index, various resolvers are run, which can decide for each individual file how to resolve the matter.\nThe first stage is a trivial resolver, which takes care of things like unchanged files, cases where one branch has modified a file while the other didn't, or where both branches contain the same new version of the file.\nAfterwards, it's plugins that look at the remaining cases. There is a plugin that handles text files by identifying individual changes (like diff) in one branch and trying to apply those to the other branch, falling back on placing conflict markers if that doesn't work. You can easily hook in your own merge tool at this point, for example, you could write a tool that knows how to merge XML files without violating well-formedness, or that gives a graphical user interface that allows interactive editing and a side-by-side view (for example, kdiff3 does that).\nSo the presentation of conflicts is really a matter of the plugin used; the default plugin for text files will use the same style as CVS did, because people and tools are used to it, and the conflict markers are a known syntax error in almost any programming language."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Git - finding a filename from a SHA1\nI added a file to the index with:\ngit add somefile.txt\n\nI then got the SHA1 for this file with:\ngit hash-object somefile.txt\n\nI now have a SHA1 and I would like to retrieve the filename of the object in the index using the SHA1.\ngit show 5a5bf28dcd7944991944cc5076c7525439830122\n\nThis command returns the file contents but not the name of the file. \nHow do I get the full filename and path back from the SHA1?"
},
{
"role": "assistant",
"content": "There's no such direct mapping in git as the name of the file is part of the tree object that contains the file, not of the blob object that is the file's contents.\nIt's not a usual operation to want to retrieve a file name from a SHA1 hash so perhaps you could expand on a real world use case for it?\nIf you're looking at current files (i.e. the HEAD commit) you can try the following.\ngit ls-tree -r HEAD | grep <SHA1>\n\nIf you want to find the contents in previous commits you'll need to do something more like this.\ngit rev-list <commit-list> | \\\nxargs -n1 -iX sh -c \"git ls-tree -r X | grep <SHA1> && echo X\""
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to duplicate a git repository? (without forking)\nI have two repositories, and I need to copy whole of one onto the other empty one which has different access levels from the first one. The copy and the mother repository should not be linked together.\nI am new to git and it would be awesome if someone could help me with this."
},
{
"role": "assistant",
"content": "See https://help.github.com/articles/duplicating-a-repository\nShort version:\nIn order to make an exact duplicate, you need to perform both a bare-clone and a mirror-push:\nmkdir foo; cd foo \n# move to a scratch dir\n\ngit clone --bare https://github.com/exampleuser/old-repository.git\n# Make a bare clone of the repository\n\ncd old-repository.git\ngit push --mirror https://github.com/exampleuser/new-repository.git\n# Mirror-push to the new repository\n\ncd ..\nrm -rf old-repository.git \n# Remove our temporary local repository\n\nNOTE: the above will work fine with any remote git repo, the instructions are not specific to github\nThe above creates a new remote copy of the repo. Then clone it down to your working machine."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Cross-Origin Resource Sharing on GitHub Pages\n\nIs there a way to enable Cross-Origin Resource Sharing (CORS) for a static page hosted on GitHub Pages to allow cross-origin requests in Javascript?\nFor example, can we instruct GH Pages somehow to add these HTTP response headers:\nAccess-Control-Allow-Origin:* \nAccess-Control-Allow-Methods:GET,POST\nAccess-Control-Max-Age: 1000\nAccess-Control-Allow-Headers:*\n\nCouldn't find anything in their documentation, and this ...\n\n...GitHub Pages does not support customer server configuration files\n such as .htaccess or .conf...\n\n... doesn't sound very promising - or is there a way?"
},
{
"role": "assistant",
"content": "EDIT: Yay! Looks like GitHub Pages now supports CORS: https://twitter.com/invisiblecomma/status/575219895308324864\nThis can be verified by curling a request to enable-cors.org (which is hosted on GitHub Pages). Running this command: curl -v enable-cors.org > /dev/null returns an Access-Control-Allow-Origin: * header.\nThere's no way to support CORS on GitHub Pages, though I'd love to see this feature. We host http://enable-cors.org on GitHub Pages, and we can't enable CORS on the site itself :)\n\nUpdate\nAs noted by @Styx GitHub Pages now always redirect to HTTPS. So if you want to confirm for yourself that all origins are allowed, for a particular site using GitHub pages, try curl with -L (to follow the redirects that are involved). E.g.:\n$ curl -vL square.github.io/okhttp 2>&1 | fgrep -i access-control-allow-origin"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Can't login to GitHub from SourceTree anymore\n\nI was able to login up until today when it just stopped working. I'm using a Windows 7 machine. I have 2-factor authentication.\nI've tried personal access tokens. I've tried deleting my credentials and re-adding them. I've tried nuking and/or updating credentials in Windows Credentials Manager. I've tried OATH vs Basic authentication. No luck. It just keeps asking me for \"Username or email\" and \"password\".\nI've tried changing my GitHub password. I've tried authenticating with OAuth (SourceTree says it's connected, but then I get the login screen again).\nCan anybody out there give me a list of steps to get back into our repo from SourceTree? I'm blocked now and unable to do work until I get this fixed."
},
{
"role": "assistant",
"content": "Your git is out of date. You need to update your system git and then switch ST to use that. I think ST's embedded git needs to update the latest git version available on their server (complete guess). In the meantime, this works for me."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to do hotfixes with GitHub Pull Requests\n\nCaveat: I am fairly new to both git and GitHub.\nSo, in my current setup, my team uses git flow Hotfixes (usually started and finished by a graphical tool such as GitKraken or IntelliJ) to make changes that have to be merged into two branches and pushed upstream in both. So for example the flow would be:\n\nPull latest from master\nStart hotfix\nCommit changes\nMerge hotfix branch into both master and develop and push both upstream\n\nWe're now looking at moving our code into GitHub and would like to start using Pull Requests, for a couple of reasons:\n\nCI hooks to run tests and stuff\na place to put code-specific comments not directly related to the underlying \"issue\"\navoiding the need for everyone to constantly be pulling the latest master/develop to their local machine so that they can merge changes\n\nBut in the case of Hotfixes, I'm not sure what to do because I'm merging into two branches but it really is one \"action\" so manually creating two pull requests seems weird, particularly since step 4) in our current flow is a single click.\nIs there a smart way of handling this? My ideal case would be that pushing the Merge button on the Pull Request would just merge into both, but that doesn't seem to be an available option."
},
{
"role": "assistant",
"content": "As you mentioned, a Pull Request has only one target branch, so you won't be able to push the hotfix to both master and develop by merging one Pull Request.\nI'm also surprised you mention your step #4 - merging the hotfix branch to both master and develop and push upstream - is one action. While there's a high chance the merge from hotfix to master won't run into merge conflicts, I can't say the same for the merge from hotfix to develop since it could have been worked on since the last deployment to production.\nMy recommendation would then be the following:\n\nCreate one PR from hotfix to master and have someone review it to validate the fix\nOnce it's merged into master, create another PR from hotfix to develop and see if you run into merge conflicts\n\n\nIf that's the case, resolve the merge conflicts so the PR ends up in a state to be merged, and have someone review the PR\nIf there's no merge conflicts, then have someone review the PR\n\n\n\nAn alternative solution, if you really want to go down the automated path, would be to leverage both GitHub webhooks and API.\nThe webhook would allow you to be notified when a PR is merged. You could inspect the payload to make sure that the base branch starts with hotfix/ and the target branch is master. You could then react to that event by using the API to create a new PR from the same hotfix branch to develop.\nIt will involve some development, and the effort might not be worth since creating a PR via the UI is still quite easy and quick."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Gitlab-CI: gitlab ci trigger build only for merge request\n\nIm using gitlab 8.1.4. And using gitlab-ci thats comes built-in. By default, gitlab-ci is triggering build for every push. How can make it trigger only during creation of merge request?\nThanks in advance"
},
{
"role": "assistant",
"content": "Try the following into your .gitlab-ci.yml file.\nstage: build\nscript:\n - xxxxx\nartifacts:\n paths:\n - xxxxx\ntags:\n - xxxx\nonly:\n - merge_requests\n\nSource: https://docs.gitlab.com/ee/ci/yaml/#only-and-except-simplified"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How can I reconcile detached HEAD with master/origin?\nI'm new at the branching complexities of Git. I always work on a single branch and commit changes and then periodically push to my remote origin.\nSomewhere recently, I did a reset of some files to get them out of commit staging, and later did a rebase -i to get rid of a couple recent local commits. Now I'm in a state I don't quite understand.\nIn my working area, git log shows exactly what I'd expect-- I'm on the right train with the commits I didn't want gone, and new ones there, etc.\nBut I just pushed to the remote repository, and what's there is different-- a couple of the commits I'd killed in the rebase got pushed, and the new ones committed locally aren't there. \nI think \"master/origin\" is detached from HEAD, but I'm not 100% clear on what that means, how to visualize it with the command line tools, and how to fix it."
},
{
"role": "assistant",
"content": "First, let’s clarify what HEAD is and what it means when it is detached. \nHEAD is the symbolic name for the currently checked out commit. When HEAD is not detached (the “normal”1 situation: you have a branch checked out), HEAD actually points to a branch’s “ref” and the branch points to the commit. HEAD is thus “attached” to a branch. When you make a new commit, the branch that HEAD points to is updated to point to the new commit. HEAD follows automatically since it just points to the branch.\n\ngit symbolic-ref HEAD yields refs/heads/master\nThe branch named “master” is checked out.\ngit rev-parse refs/heads/master yield 17a02998078923f2d62811326d130de991d1a95a\nThat commit is the current tip or “head” of the master branch.\ngit rev-parse HEAD also yields 17a02998078923f2d62811326d130de991d1a95a\nThis is what it means to be a “symbolic ref”. It points to an object through some other reference.\n(Symbolic refs were originally implemented as symbolic links, but later changed to plain files with extra interpretation so that they could be used on platforms that do not have symlinks.)\n\nWe have HEAD → refs/heads/master → 17a02998078923f2d62811326d130de991d1a95a\nWhen HEAD is detached, it points directly to a commit—instead of indirectly pointing to one through a branch. You can think of a detached HEAD as being on an unnamed branch. \n\ngit symbolic-ref HEAD fails with fatal: ref HEAD is not a symbolic ref\ngit rev-parse HEAD yields 17a02998078923f2d62811326d130de991d1a95a\nSince it is not a symbolic ref, it must point directly to the commit itself.\n\nWe have HEAD → 17a02998078923f2d62811326d130de991d1a95a\nThe important thing to remember with a detached HEAD is that if the commit it points to is otherwise unreferenced (no other ref can reach it), then it will become “dangling” when you checkout some other commit. Eventually, such dangling commits will be pruned through the garbage collection process (by default, they are kept for at least 2 weeks and may be kept longer by being referenced by HEAD’s reflog).\n1\nIt is perfectly fine to do “normal” work with a detached HEAD, you just have to keep track of what you are doing to avoid having to fish dropped history out of the reflog.\n\nThe intermediate steps of an interactive rebase are done with a detached HEAD (partially to avoid polluting the active branch’s reflog). If you finish the full rebase operation, it will update your original branch with the cumulative result of the rebase operation and reattach HEAD to the original branch. My guess is that you never fully completed the rebase process; this will leave you with a detached HEAD pointing to the commit that was most recently processed by the rebase operation.\nTo recover from your situation, you should create a branch that points to the commit currently pointed to by your detached HEAD:\ngit branch temp\ngit checkout temp\n\n(these two commands can be abbreviated as git checkout -b temp)\nThis will reattach your HEAD to the new temp branch.\nNext, you should compare the current commit (and its history) with the normal branch on which you expected to be working:\ngit log --graph --decorate --pretty=oneline --abbrev-commit master origin/master temp\ngit diff master temp\ngit diff origin/master temp\n\n(You will probably want to experiment with the log options: add -p, leave off --pretty=… to see the whole log message, etc.)\nIf your new temp branch looks good, you may want to update (e.g.) master to point to it:\ngit branch -f master temp\ngit checkout master\n\n(these two commands can be abbreviated as git checkout -B master temp)\nYou can then delete the temporary branch:\ngit branch -d temp\n\nFinally, you will probably want to push the reestablished history:\ngit push origin master\n\nYou may need to add --force to the end of this command to push if the remote branch can not be “fast-forwarded” to the new commit (i.e. you dropped, or rewrote some existing commit, or otherwise rewrote some bit of history).\nIf you were in the middle of a rebase operation you should probably clean it up. You can check whether a rebase was in process by looking for the directory .git/rebase-merge/. You can manually clean up the in-progress rebase by just deleting that directory (e.g. if you no longer remember the purpose and context of the active rebase operation). Usually you would use git rebase --abort, but that does some extra resetting that you probably want to avoid (it moves HEAD back to the original branch and resets it back to the original commit, which will undo some of the work we did above)."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-log - Show commit logs notes.rewrite.<command>"
},
{
"role": "assistant",
"content": "When rewriting commits with <command> (currently amend or rebase ), if this variable is false , git will not copy\nnotes from the original to the rewritten commit. Defaults to true . See also \" notes.rewriteRef \" below. This setting can be overridden with the GIT_NOTES_REWRITE_REF environment variable, which must be a colon separated list of refs or\nglobs."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "List commits between 2 commit hashes in git\nI know there has been very similar questions here, but they didn't solve my problem.\nPerhaps there's something I'm not understanding well.\nThis is a portion of the commit history of fitnesse (https://github.com/unclebob/fitnesse/):\n* | | | | | | | | | | | | | | | fa86be8 Avoid possible issue when using CachingPage under heavy memory load.\n|/ / / / / / / / / / / / / / / \n* | | | | | | | | | | | | | | 7b4a07a Merge pull request #256 from barredijkstra/fitnesse_issue_250\n|\\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \n| * | | | | | | | | | | | | | | ecf5891 Fixed test checking for OS specific exception message.\n| * | | | | | | | | | | | | | | 082236e Added rendering of cause exceptions. Fix for unclebob/fitnesse#250\n* | | | | | | | | | | | | | | | a92b37f Merge pull request #243 from amolenaar/fix/243-hash-table-rendering\n\nI want the list of commits between 2 commit hashes. In this particular case, I want the commits between ecf5891 and 7b4a07a, and I expect the result to be:\necf5891\n7b4a07a\n\nSi far I've been using git rev-list commit_hash_from_here^..commit_hash_up_to_here and it has worked fine with linear history. However, in this case I get a lot more commits.\nI've tried this and it works just as expected:\ngit log --since='<date ecf5891>' --until='<date 7b4a07a>'\n\n(I've manually searched for those 2 dates).\nOne possible solution is to get the 2 dates and just do that, but I think there should be a better way. \nEdit:\n7b4a07a parents are ecf5891 and a92b37f. So far, the solutions work fine if I want to go from ecf5891 to 7b4a07a, but if I want to go from a92b37f to 7b4a07a I want to get:\n7b4a07a\necf5891\n082236e\na92b37f\n\nbut I don't get a92b37f"
},
{
"role": "assistant",
"content": "I think that you`re looking for --ancestry-path, in your case:\ngit rev-list --ancestry-path 7b4a07a..ecf5891"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-apply - Apply a patch to files and/or to the index --cached"
},
{
"role": "assistant",
"content": "Apply the patch to just the index, without touching the working\ntree. If --check is in effect, merely check that it would\napply cleanly to the index entry."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Gitlab CI + Docker Hub: requested access to the resource is denied\n\nI'm trying to push my image to my docker repositoy repository using gitlab-ci, but i'm receiving the error:\ndenied: requested access to the resource is denied\nERROR: Job failed: exit code 1\nMy .gitlab-ci.yml\n# This file is a template, and might need editing before it works on your project.\n# Official docker image.\nimage: docker:latest\n\nservices:\n - docker:dind\n\nbefore_script:\n - docker version\n - docker-compose version\n - docker login -u $USER -p $PASS index.docker.io\n\n\nbuild-master:\n stage: build\n script:\n - apk add --no-cache py-pip\n - pip install docker-compose \n - docker build --pull -t index.docker.io/$REPOSITORY .\n - docker push index.docker.io/$REPOSITORY\n only:\n - master\n tags:\n - docker\n\nbuild:\n stage: build\n script:\n - docker build --pull -t index.docker.io/$REPOSITORY:latest .\n - docker push index.docker.io/$REPOSITORY:latest\n except:\n - master\n tags:\n - docker\n\nHe build the image correctly, but when go to push\nThe push refers to repository [docker.io/$REPOSITORY]\nfc57a6fc4d42: Preparing\n09b261acf68f: Preparing\n04ea2928643d: Preparing\n1132926ce5ae: Preparing\nde09db5a8cb2: Preparing\n0b75a2e7b59f: Preparing\nd01d9d1902f1: Preparing\n3dab7cdf2eed: Preparing\n1da4e8fff32b: Preparing\n23c522961836: Preparing\na51421a28d33: Preparing\n8b1c06910686: Preparing\n30e8a3d88591: Preparing\nfd8fae5cd65a: Preparing\n6b68dfad3e66: Preparing\ncd7100a72410: Preparing\n0b75a2e7b59f: Waiting\nd01d9d1902f1: Waiting\n3dab7cdf2eed: Waiting\n1da4e8fff32b: Waiting\n23c522961836: Waiting\na51421a28d33: Waiting\n8b1c06910686: Waiting\n30e8a3d88591: Waiting\nfd8fae5cd65a: Waiting\n6b68dfad3e66: Waiting\ncd7100a72410: Waiting\ndenied: requested access to the resource is denied\nERROR: Job failed: exit code 1\n\nI change the repository name for the $REPOSITORY only for paste here.\nI already give the right permissions on hub.docker.com for the user has make the docker login, has a colaborator on the repository.\nThanks"
},
{
"role": "assistant",
"content": "use $CI_REGISTRY and $CI_PROJECT_PATH.\nExample code:\n- docker login -u gitlab-ci-token -p $CI_JOB_TOKEN $CI_REGISTRY/$CI_PROJECT_PATH\n- docker build -t $CI_REGISTRY/$CI_PROJECT_PATH/name:latest\n- docker push $CI_REGISTRY/$CI_PROJECT_PATH/name:latest"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git workflow: Can I prevent a certain file from being merged to another branch but still keep it under version control?\nI have a repository with two branches: live and stage. The repository holds code for a web based application. I would like to maintain two different .htaccess files for the stage and live branches, but still keep them version controlled, since the nature of serving a stage site is a little bit different (right now for instance, I want the caches to be timed differently).\nI'm a novice with git so there is probably an easy explanation, but I'd like to have a workflow where when I was in live and I pulled changes (simple git merge stage), I didn't overwrite the existing .htaccess in the live branch. Is there any way to configure this? Am I missing some big concept in git?\nLikewise, there is also a chunk of a (but possibly many) .html files where I would like to keep track of changes but not merge them back into live. Just to be clear I want live and stage to got keep track of changes in these files, but know not to merge those certain changes when doing merges."
},
{
"role": "assistant",
"content": "I found an answer on another question on Stack Overflow, credit goes to fcurella:\n\nLet's say you want to exclude the file config.php\nOn branch A:\n\nCreate a file named .gitattributes in the same dir, with this line: config.php merge=ours. This tells git what strategy to use when merging the file. In this case it always keep your version, ie. the version on the branch you are merging into.\nAdd the .gitattributes file and commit\n\nOn branch B: repeat steps 1-2\nTry merging now. Your file should be left untouched.\n\nThis seems like a more scalable solution."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-show - Show various types of objects --abbrev-commit"
},
{
"role": "assistant",
"content": "Instead of showing the full 40-byte hexadecimal commit object\nname, show a prefix that names the object uniquely.\n\"--abbrev=<n>\" (which also modifies diff output, if it is displayed)\noption can be used to specify the minimum length of the prefix. This should make \"--pretty=oneline\" a whole lot more readable for\npeople using 80-column terminals."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-shortlog - Summarize git log output --invert-grep"
},
{
"role": "assistant",
"content": "Limit the commits output to ones with a log message that do not\nmatch the pattern specified with --grep=<pattern> ."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-config - Get and set repository or global options color.grep.<slot>"
},
{
"role": "assistant",
"content": "Use customized color for grep colorization. <slot> specifies which\npart of the line to use the specified color, and is one of context non-matching text in context lines (when using -A , -B , or -C ) filename filename prefix (when not using -h ) function function name lines (when using -p ) lineNumber line number prefix (when using -n ) column column number prefix (when using --column ) match matching text (same as setting matchContext and matchSelected ) matchContext matching text in context lines matchSelected matching text in selected lines. Also, used to customize the following git-log subcommands: --grep , --author , and --committer . selected non-matching text in selected lines. Also, used to customize the\nfollowing git-log subcommands: --grep , --author and --committer . separator separators between fields on a line ( : , - , and = )\nand between hunks ( -- )"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Configuring user and password with Git Bash\n\nI am using Git Bash on Windows 7. We are using GitHub as our repository origin.\nEvery time I push or pull I have to provide user and password credentials. I know that my SSH keys are set up correctly, otherwise I would not be able to access the repository. (That is, once I enter my credentials the push/pull works correctly.)\nI have entered\ngit config --global user.name myusername\ngit config --global user.email myemail\ngit config --global github.user myusername\ngit config --global github.token mytoken\n\nBut nonetheless I am being asked for credentials each and every time I push/pull."
},
{
"role": "assistant",
"content": "Make sure you are using the SSH URL for the GitHub repository rather than the HTTPS URL. It will ask for username and password when you are using HTTPS and not SSH. You can check the file .git/config or run git config -e or git remote show origin to verify the URL and change it if needed.\nYou can change the URL with: [1]\ngit remote set-url origin git+ssh://[email protected]/username/reponame.git\n\n[1] This portion incorporates the answer to this question."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Git error, need to remove large file\nI am getting this error when I try to push to git and I have no idea how to fix it.\nCounting objects: 1239, done.\nDelta compression using up to 4 threads.\nCompressing objects: 100% (1062/1062), done.\nWriting objects: 100% (1239/1239), 26.49 MiB | 679.00 KiB/s, done.\nTotal 1239 (delta 128), reused 0 (delta 0)\nremote: warning: File log/development.log is 98.59 MB; this is larger than GitHub's recommended maximum file size of 50.00 MB\nremote: error: GH001: Large files detected. You may want to try Git Large File Storage - https://git-lfs.github.com.\nremote: error: Trace: efd2d13efa4a231e3216dad097ec25d6\nremote: error: See http://git.io/iEPt8g for more information.\nremote: error: File log/development.log is 108.86 MB; this exceeds GitHub's file size limit of 100.00 MB\nremote: error: File log/development.log is 108.74 MB; this exceeds GitHub's file size limit of 100.00 MB\nremote: error: File log/development.log is 108.56 MB; this exceeds GitHub's file size limit of 100.00 MB\nremote: error: File log/development.log is 106.58 MB; this exceeds GitHub's file size limit of 100.00 MB\nremote: error: File log/development.log is 103.70 MB; this exceeds GitHub's file size limit of 100.00 MB\nTo [email protected]:myUsername/myRepo.git\n! [remote rejected] master -> master (pre-receive hook declined)\nerror: failed to push some refs to '[email protected]:myUsername/myRepo.git'\n\nI'm guessing I need to remove the large file from the commit, but how do I do that?"
},
{
"role": "assistant",
"content": "To remove large files, GitHub suggests:\n$ git rm --cached giant_file\n# Stage our giant file for removal, but leave it on disk\n\ngit commit --amend -CHEAD\n# Amend the previous commit with your change\n# Simply making a new commit won't work, as you need\n# to remove the file from the unpushed history as well\n\ngit push\n# Push our rewritten, smaller commit\n\nOr if you want more general information on how to work with large files on GitHub.\nAnd next time add /log in your .gitignore"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "In Git how can you check which repo in Github you are pushing to from the command line?\n\nI have several projects I am working on. I am constantly pulling and pushing. Recently I made some changes to one of my files, added and committed and decided to push my project A, however it pushed into my Github Project B. I then did git pull for kicks and it this happened.\n\nbranch master -> FETCH_HEAD\nAlready up-to-date.\n\nIt did not pull none of my files from Project B. I then did git status and it showed every single file/folders in my directory as needing to be committed. How would I know which \"init\" I am on? How can I switch out of this state and how can I disregard these blind commits without losing my files?"
},
{
"role": "assistant",
"content": "I think you need to reconfig git remote\ntype git remote -v and see if there's a mismatch or not.\nIf there is, follow this instruction from github: https://help.github.com/articles/changing-a-remote-s-url/"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to do 'git checkout --theirs' for multiple files (or all unmerged files)\nSay I have this after attempting a merge and upon entering git status:\n# Unmerged paths:\n# (use \"git add/rm <file>...\" as appropriate to mark resolution)\n#\n# added by them: myfile1.xhtml\n# added by them: myfile2.xhtml\n# added by them: myfile3.xhtml\n\n... and I know I want to do this for each of those files:\ngit checkout --theirs myfile1.xhtml\ngit add myfile1.xhtml\n\n... but there are many of them. How might I do them as a batch?"
},
{
"role": "assistant",
"content": "The solution for my case ended up being to simply use a wildcard in the directory path, since the files were grouped:\ngit checkout --theirs directory_name/*\ngit add directory_name/*\n\nThis may also work, according to helios456:\ngit checkout --theirs directory_name/."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to apply `git diff` patch without Git installed?\nHow can my client apply patch created by git diff without git installed?\nI have tried to use patch command but it always asks file name to patch."
},
{
"role": "assistant",
"content": "git diff > patchfile\n\nand\npatch -p1 < patchfile\n\nwork but as many people noticed in comments and other answers patch does not understand adds, deletes and renames. There is no option but git apply patchfile if you need handle file adds, deletes and renames.\n\nEDIT December 2015\nLatest versions of patch command (2.7, released in September 2012) support most features of the \"diff --git\" format, including renames and copies, permission changes, and symlink diffs (but not yet binary diffs) (release announcement). \nSo provided one uses current/latest version of patch there is no need to use git to be able to apply its diff as a patch."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Remove html extension from GitHub Pages\n\nI'm using GitHub pages to host my latest site:\nhttp://mysite.github.io/\n\nI was wondering if there was a way to remove the .html extension from the end of sub-pages:\nhttp://mysite.github.io/contact.html\n\nsince there is no access to the server."
},
{
"role": "assistant",
"content": "It already works and you don't have to do anything\nI'm not sure if you are already aware of that or not but to remove .html extension from GitHub Pages all you have to do is remove .html extension from your links.\nIn other words it already works and you don't have to do anything. You don't have to use subdirectories, CNAME, redirects, Jekyll _config.yml, YAML front-matter or any other hack suggested in all of the answers here.\nExamples\nFor example you can use:\n\nhttps://rsp.github.io/gh-pages-no-extension/test1\n\ninstead of:\n\nhttps://rsp.github.io/gh-pages-no-extension/test1.html\n\nand it displays the same file.\nJust change the links in your links and that's it.\nTests\nI made some tests to demonstrate how it really works where you can click links and it highlights which file is loaded with which URL, including warnings about insecure redirects in certain cases.\nFor eaxample, the link:\n\nhttps://rsp.github.io/gh-pages-no-extension/test1\n\nshows that it is displayed by the test1 in the URL but actually displays the file test1.html:\n\nProblems with other solutions\nUsing things like index.html in special subdirectories as suggested here in other answers will not do what you want, which is simply serving the example.com/name.html when asked for example.com/name, but would instead give you a 301 redirect to example.com/name/ (note the trailing slash) which in turn would give you the contents of example.com/name/index.html file.\nThat leads to the following problems: you are in a different directory and you need to use <a href=\"../name\"> instead of just <a href=\"name\"> for links to other pages on the same level and the same goes for all assets (or you can use absolute paths as someone suggested which is not a good idea on GitHub pages - especially project pages - because after forks and projects renaming you have to remember to update all of the links and js/css assets in all of the html files).\nThe other thing is that now you have a useless redirect for every navigation - which incidentally redirects from HTTPS to HTTP (from secure URLs without the slash to insecure URLs with a slash), e.g. see:\n\nhttps://rsp.github.io/gh-pages-no-extension/dir (secure HTTPS)\n\nwhich (at the time of writing) redirects to:\n\nhttp://rsp.github.io/gh-pages-no-extension/dir/ (insecure HTTP)\n\nand NOT to:\n\nhttps://rsp.github.io/gh-pages-no-extension/dir/ (secure HTTPS)\n\nas you might expect, so make sure that you are aware of that. See:\n\n(Note that this image is linked to a secure HTTPS URL but you end up using an insecure HTTP connection - you may need to use incognito mode to see that.)\nThis is how the headers look like, as of June 17, 2016:\n$ curl -I https://rsp.github.io/gh-pages-no-extension/dir\nHTTP/1.1 301 Moved Permanently\nServer: GitHub.com\nContent-Type: text/html\nLocation: http://rsp.github.io/gh-pages-no-extension/dir/\n... ^^^^\n\nHopefully GitHub will fix that in the future.\n(I discovered it when I was writing this answer almost a year ago and this problem is still present as of June 2016.)\nThough strangely enough, as of June 17, 2016 (I'm not sure if it always was the case because I noticed it recently while updating this answer) this URL:\n\nhttps://rsp.github.io/gh-pages-no-extension (secure HTTPS)\n\nredirects to:\n\nhttps://rsp.github.io/gh-pages-no-extension/ (secure HTTPS)\n\nas it should. See the headers:\n$ curl -I https://rsp.github.io/gh-pages-no-extension\nHTTP/1.1 301 Moved Permanently\nServer: GitHub.com\nContent-Type: text/html\nLocation: https://rsp.github.io/gh-pages-no-extension/\n... ^^^^^\n\nThe only difference is that it is a project root URL and not a deeper directory inside the project (see the project structure) so the buggy redirect seems to be present only in deep links inside a project's GitHub Pages and on one browser I tested only when you use incognito mode.\nThe bottom line is that you need to be careful. My advice would be to avoid all redirects altogether and only use those URLs that don't result in any redirects at all."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-gc - Cleanup unnecessary files and optimize the local repository gc.reflogExpireUnreachable gc.<pattern>.reflogExpireUnreachable"
},
{
"role": "assistant",
"content": "git reflog expire removes reflog entries older than\nthis time and are not reachable from the current tip;\ndefaults to 30 days. The value \"now\" expires all entries\nimmediately, and \"never\" suppresses expiration altogether.\nWith \"<pattern>\" (e.g. \"refs/stash\")\nin the middle, the setting applies only to the refs that\nmatch the <pattern>. These types of entries are generally created as a result of using git\ncommit --amend or git rebase and are the commits prior to the amend\nor rebase occurring. Since these changes are not part of the current\nproject most users will want to expire them sooner, which is why the\ndefault is more aggressive than gc.reflogExpire ."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Git Hub Clone All Branches At Once\nI'm trying to clone an entire repository onto my machine using linux. I used \ngit clone <url> \n\nI then went into the folder where it was downloaded and typed\ngit branch \n\nin the terminal. It's only showing me master and not other branches which were in the remote repository. How do I clone all branches?\nI know that for each branch in the remote I can separately use \ngit checkout -b <name of local branch> origin/<name of remote branch>\n\nbut is there any way other than that?"
},
{
"role": "assistant",
"content": "(1) Inside git local repostitory, create a new sh file\ntouch getAllBranches.sh\nvi getAllBranches.sh\n\n(2) Insert the below content to getAllBranches.sh file:\nfor branch in `git branch -a | grep remotes | grep -v HEAD | grep -v master `; do\n git branch --track ${branch#remotes/origin/} $branch\ndone\n\n(3) Get all branches:\nchmod +x getAllBranches.sh \nsh getAllBranches.sh\n\n(4) Check result at local repository:\ngit branch\n\nFor example, I use repository: https://github.com/donhuvy/spring-boot\nAs you can see, I have fetched all branches to local machine:"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-fsck - Verifies the connectivity and validity of the objects in the database largePathname"
},
{
"role": "assistant",
"content": "(WARN) A tree contains an entry with a very long path name. If\nthe value of fsck.largePathname contains a colon, that value\nis used as the maximum allowable length (e.g., \"warn:10\" would\ncomplain about any path component of 11 or more bytes). The\ndefault value is 4096."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-show - Show various types of objects ignore-all-space"
},
{
"role": "assistant",
"content": "Ignore whitespace when comparing lines. This ignores differences\neven if one line has whitespace where the other line has none."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-show - Show various types of objects -G<regex>"
},
{
"role": "assistant",
"content": "Look for differences whose patch text contains added/removed\nlines that match <regex>. To illustrate the difference between -S<regex> --pickaxe-regex and -G<regex> , consider a commit with the following diff in the same\nfile: + return frotz(nitfol, two->ptr, 1, 0);\n...\n- hit = frotz(nitfol, mf2.ptr, 1, 0); While git log -G\"frotz\\(nitfol\" will show this commit, git log\n-S\"frotz\\(nitfol\" --pickaxe-regex will not (because the number of\noccurrences of that string did not change). Unless --text is supplied patches of binary files without a textconv\nfilter will be ignored. See the pickaxe entry in gitdiffcore for more\ninformation."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-clean - Remove untracked files from the working tree -i --interactive"
},
{
"role": "assistant",
"content": "Show what would be done and clean files interactively. See\n“Interactive mode” for details.\nConfiguration variable clean.requireForce is ignored, as\nthis mode gives its own safety protection by going interactive."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-rev-list - Lists commit objects in reverse chronological order --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-rev-list - Lists commit objects in reverse chronological order %n"
},
{
"role": "assistant",
"content": "newline"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git how to change default branch for everything I do?\n\nBecause of github changing the default branch from master to main all of my pushes end up in a separate branch instead of the main one and I can't change the default. When I start a program and make my first push, git tells me main doesn't exist and I always have to push to master instead."
},
{
"role": "assistant",
"content": "Following the FAQ article \"How to Rename the master branch to main in Git\", and the GitHub documentation itself, you can:\n\nrename your local branch from master to main: git branch -m master main\npush to main: git push -u origin main\nupdate your default branch on GitHub side:\n\nThen delete the remote master branch: git push origin --delete master\n\nFinally, as I documented in \"How can I create a Git repository with the default branch name other than \"master\"?\", don't forget a:\ngit config --global init.defaultBranch main\n\n(See commit 32ba12d, with Git 2.28+, Q3 2020)\nYour next new repositories will use the right branch name by default."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git commit --amend without asking for message [duplicate]\nThis question already has answers here:\n \n \n\n\n\n\nHow to amend a commit without changing commit message (reusing the previous one)?\n\n (8 answers)\n \n\nClosed 7 years ago.\n\n\n\nFrom time to time I find myself commit-amending using the same message.\nTypically, I do:\n\nAdd my changes to staging area.\nDo git commit --amend.\nWait for the text editor to open.\nSave and close it (without changing the message).\n\nThere is anyway to tell git that I don't want to change the commit message (skipping the step of opening my text editor and saving the message)? Like:\n\nAdd my changes to staging area.\nTell git to amend my staging area to the last commit without asking me for another message.\n\n\nI know I can avoid git firing up my text editor by doing git commit --amend -m \"<message>\". But this way I would have to retype the message."
},
{
"role": "assistant",
"content": "Try git commit --amend --no-edit."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-rev-list - Lists commit objects in reverse chronological order --ancestry-path[=<commit>]"
},
{
"role": "assistant",
"content": "Limit the displayed commits to those which are an ancestor of\n<commit>, or which are a descendant of <commit>, or are <commit>\nitself. As an example use case, consider the following commit history: D---E-------F\n\t / \\ \\\n\t B---C---G---H---I---J\n\t / \\\n\tA-------K---------------L--M A regular D..M computes the set of commits that are ancestors of M ,\nbut excludes the ones that are ancestors of D . This is useful to see\nwhat happened to the history leading to M since D , in the sense\nthat “what does M have that did not exist in D ”. The result in this\nexample would be all the commits, except A and B (and D itself,\nof course). When we want to find out what commits in M are contaminated with the\nbug introduced by D and need fixing, however, we might want to view\nonly the subset of D..M that are actually descendants of D , i.e.\nexcluding C and K . This is exactly what the --ancestry-path option does. Applied to the D..M range, it results in: E-------F\n\t\t \\ \\\n\t\t G---H---I---J\n\t\t\t \\\n\t\t\t\tL--M We can also use --ancestry-path=D instead of --ancestry-path which\nmeans the same thing when applied to the D..M range but is just more\nexplicit. If we instead are interested in a given topic within this range, and all\ncommits affected by that topic, we may only want to view the subset of D..M which contain that topic in their ancestry path. So, using --ancestry-path=H D..M for example would result in: E\n\t\t \\\n\t\t G---H---I---J\n\t\t\t \\\n\t\t\t\tL--M Whereas --ancestry-path=K D..M would result in K---------------L--M"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-clone - Clone a repository into a new directory --progress"
},
{
"role": "assistant",
"content": "Progress status is reported on the standard error stream\nby default when it is attached to a terminal, unless --quiet is specified. This flag forces progress status even if the\nstandard error stream is not directed to a terminal."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-config - Get and set repository or global options selected"
},
{
"role": "assistant",
"content": "non-matching text in selected lines. Also, used to customize the\nfollowing git-log subcommands: --grep , --author and --committer ."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": ".gitignore all the .DS_Store files in every folder and subfolder\nI've added .DS_Store to the .gitignore file, but it seems that it is only ignoring .DS_Store in the root directory, not in every folder and subfolder.\nHow do I fix this?"
},
{
"role": "assistant",
"content": "I think the problem you're having is that in some earlier commit, you've accidentally added .DS_Store files to the repository. Of course, once a file is tracked in your repository, it will continue to be tracked even if it matches an entry in an applicable .gitignore file.\nYou have to manually remove the .DS_Store files that were added to your repository. You can use \ngit rm --cached .DS_Store\n\nOnce removed, git should ignore it. You should only need the following line in your root .gitignore file: .DS_Store. Don't forget the period!\ngit rm --cached .DS_Store\n\nremoves only .DS_Store from the current directory. You can use \nfind . -name .DS_Store -print0 | xargs -0 git rm --ignore-unmatch\n\nto remove all .DS_Stores from the repository.\nFelt tip: Since you probably never want to include .DS_Store files, make a global rule. First, make a global .gitignore file somewhere, e.g. \necho .DS_Store >> ~/.gitignore_global\n\nNow tell git to use it for all repositories: \ngit config --global core.excludesfile ~/.gitignore_global\n\nThis page helped me answer your question."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Renaming a branch in GitHub\n\nI just renamed my local branch using\ngit branch -m oldname newname\n\nbut this only renames the local version of the branch. How can I rename the one on GitHub?"
},
{
"role": "assistant",
"content": "As mentioned, delete the old one on GitHub and re-push, though the commands used are a bit more verbose than necessary:\ngit push origin :name_of_the_old_branch_on_github\ngit push origin new_name_of_the_branch_that_is_local\n\nDissecting the commands a bit, the git push command is essentially:\ngit push <remote> <local_branch>:<remote_branch>\n\nSo doing a push with no local_branch specified essentially means \"take nothing from my local repository, and make it the remote branch\". I've always thought this to be completely kludgy, but it's the way it's done.\nAs of Git 1.7 there is an alternate syntax for deleting a remote branch:\ngit push origin --delete name_of_the_remote_branch\n\nAs mentioned by @void.pointer in the comments\n\nNote that you can combine the 2 push operations:\ngit push origin :old_branch new_branch\nThis will both delete the old branch and push the new one.\n\nThis can be turned into a simple alias that takes the remote, original branch and new branch name as arguments, in ~/.gitconfig:\n[alias]\n branchm = \"!git branch -m $2 $3 && git push $1 :$2 $3 -u #\"\n\nUsage:\ngit branchm origin old_branch new_branch\n\nNote that positional arguments in shell commands were problematic in older (pre 2.8?) versions of Git, so the alias might vary according to the Git version. See this discussion for details."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "\"Updates were rejected because the remote contains work that you do not have locally.\" after creating a new repository on GitHub\nI created a new repo, cloned it, added files to the directory, added them with add -A, committed changes, and when I try to push using git push <repo name> master I get:\n\nhint: Updates were rejected because the remote contains work that you do not have locally. This is usually caused by another repository pushing to the same ref. You may want to first merge the remote changes (e.g.,\nhint: 'git pull') before pushing again.\n\nThis doesn't seem to make sense since it's a new repo and contains only a readme file."
},
{
"role": "assistant",
"content": "This happens if you initialized a new github repo with README and/or LICENSE file\ngit remote add origin [//your github url]\n\n//pull those changes\n\ngit pull origin main \n\n// or optionally, 'git pull origin main --allow-unrelated-histories' if you have initialized repo in github and also committed locally\n\n//now, push your work to your new repo\n\ngit push origin main\n\nNow you will be able to push your repository to github. Basically, you have to merge those new initialized files with your work. git pull fetches and merges for you. You can also fetch and merge if that suits you."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-config - Get and set repository or global options addIgnoredFile"
},
{
"role": "assistant",
"content": "Shown when the user attempts to add an ignored file to\nthe index."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "github linking with other repos\n\nI have a project that relies on two repos in github to function. \nWhen I submit my project to github how do I link to these two repos? \nShould I duplicate the files in my own repo or link to the other repo at a specific revision as I don't want it to update and cause incompatibility.\nI already created my github repo what should I do?"
},
{
"role": "assistant",
"content": "You can use git submodules to \"link\" to other projects.\nSee here - https://github.blog/2016-02-01-working-with-submodules/"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Is there a link to GitHub for downloading a file in the latest release of a repository?\n\nUsing GitHub's Release feature, it is possible to provide a link to download a specific version of the published software. However, every time a release is made, the gh-page also needs to be updated.\nIs there a way to get a link to a specific file of whatever the latest version of a software is?\ne.g., this would be a static link:\nhttps://github.com/USER/PROJECT/releases/download/v0.0.0/package.zip\nWhat I'd like is something like:\nhttps://github.com/USER/PROJECT/releases/download/latest/package.zip\n\nNOTE: The difference between this question and\n GitHub latest release is\n that this question specifically asks for getting access to the file,\n not the GitHub latest release page"
},
{
"role": "assistant",
"content": "A few years late, but I just implemented a simple redirect to support https://github.com/USER/PROJECT/releases/latest/download/package.zip. That should redirected to the latest tagged package.zip release asset. Hope it's handy!"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-rev-parse - Pick out and massage parameters @"
},
{
"role": "assistant",
"content": "@ alone is a shortcut for HEAD ."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "In Visual Studio Code How do I merge between two local branches?\nIn Visual Studio Code it seems that I am only allowed to push, pull and sync. There is documented support for merge conflicts but I can't figure out how to actually merge between two branches. The Git command line within VSC (press F1) only facillitates a subset of commands:\n\nAttempting to pull from a an alternate branch or push to an alternate branch yields:\n\nHere's the documentation on VSCode's Git\n Visual Studio Code Git Documentation\nWhat am I overlooking?"
},
{
"role": "assistant",
"content": "You can do it without using plugins.\nIn the latest version of vscode that I'm using (1.17.0) you can simply open the branch that you want (from the bottom left menu) then press ctrl+shift+p and type Git: Merge branch and then choose the other branch that you want to merge from (to the current one)"
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-show - Show various types of objects --default-prefix"
},
{
"role": "assistant",
"content": "Use the default source and destination prefixes (\"a/\" and \"b/\").\nThis overrides configuration variables such as diff.noprefix , diff.srcPrefix , diff.dstPrefix , and diff.mnemonicPrefix (see git-config (1))."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How to cancel a local git commit?\nMy issue is I have changed a file e.g.: README, added a new line 'this for my testing line' and saved the file, then I issued the following commands:\ngit status\n\n# On branch master\n# Changed but not updated:\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: README\n#\nno changes added to commit (use \"git add\" and/or \"git commit -a\")\n\n\ngit add README\n\ngit commit -a -m 'To add new line to readme'\n\nI didn't push the code to GitHub. Now I want to cancel this commit.\nFor this, I used\ngit reset --hard HEAD~1\n\nBut I lost the newly added line 'this for my testing line' from the README file.\nThis should not happen. I need the content to be there. Is there a way to retain the content and cancel my local commit?"
},
{
"role": "assistant",
"content": "Just use git reset without the --hard flag:\ngit reset HEAD~1\n\nPS: On Unix based systems you can use HEAD^ which is equal to HEAD~1. On Windows HEAD^ will not work because ^ signals a line continuation. So your command prompt will just ask you More?."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-shortlog - Summarize git log output --simplify-by-decoration"
},
{
"role": "assistant",
"content": "Commits that are referred by some branch or tag are selected."
}
] |
[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "git-svn - Bidirectional operation between a Subversion repository and Git --username=<user>"
},
{
"role": "assistant",
"content": "For transports that SVN handles authentication for (http,\nhttps, and plain svn), specify the username. For other\ntransports (e.g. svn+ssh:// ), you must include the username in\nthe URL, e.g. svn+ssh://[email protected]/project"
}
] |