Split (3)

train · 10.9k rows

messages listlengths 3 3
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-diff - Show changes between commits, commit and working tree, etc Comparing branches" }, { "role": "assistant", "content": "$ git diff topic master (1) $ git diff topic..master (2) $ git diff topic...master (3) Changes between the tips of the topic and the master branches. Same as above. Changes that occurred on the master branch since when the topic\nbranch was started off it." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Is it possible to remote count object and size of git repository?\nAssume that somewhere in the web exists public git repository. I want to clone it but firstly i need to be sure what is size of it (how much objects & kbytes like in git count-objects)\nIs there a way to do it?" }, { "role": "assistant", "content": "One little kludge you could use would be the following:\nmkdir repo-name\ncd repo-name\ngit init\ngit remote add origin <URL of remote>\ngit fetch origin\n\ngit fetch displays feedback along these lines:\nremote: Counting objects: 95815, done.\nremote: Compressing objects: 100% (25006/25006), done.\nremote: Total 95815 (delta 69568), reused 95445 (delta 69317)\nReceiving objects: 100% (95815/95815), 18.48 MiB \| 16.84 MiB/s, done.\n...\n\nThe steps on the remote end generally happen pretty fast; it's the receiving step that can be time-consuming. It doesn't actually show the total size, but you can certainly watch it for a second, and if you see \"1% ... 23.75 GiB\" you know you're in trouble, and you can cancel it." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Superscript in markdown (Github flavored)?\n\nFollowing this lead, I tried this in a Github README.md:\n<span style=\"vertical-align: baseline; position: relative;top: -0.5em;>text in superscript</span>\n\nDoes not work, the text appears as normal. Help?" }, { "role": "assistant", "content": "Use the <sup></sup> tag (<sub></sub> is the equivalent for subscripts). See this gist for an example." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How to connect existing Android Studio project to existing Github repository\n\nSo I am new to Android development and Android Studio.\nI used Android Studio to create an Android project, and each time I wanted to commit the code to GitHub, I switched over to the command line and committed/pushed the code from there. \nHowever, I realize now that Android Studio has it's own features for connecting to GitHub. I'd like to use those features. \nSince the project already exists, I prefer not to just create a new GitHub repository from Android Studio and delete the old one. I just want to connect the existing GitHub repository with the Android Studio project.\nHow can I sync these up?" }, { "role": "assistant", "content": "Maybe it is a little bit late, but if it helps to someone here is what I do in command line:\ncd <proyect folder>\ngit init\ngit remote add origin <link to repo>\ngit fetch origin\ngit checkout master\n\nnote: if there are commits on the repo it may require you to remove conflicting files\ngit add --all\ngit commit -m \"<message>\"\ngit push" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Does GitHub for Windows work with GitLab?\nWhile working on a project using GitHub I've fallen in love with GitHub for Windows as a client. Now a new project beckons where I'll be using GitLab instead of GitHub.\nWill I still be able to use GitHub for Windows as a client for GitLab? After all, they're both based on git, right? If not, what clients are available for GitLab?" }, { "role": "assistant", "content": "Yes, you can use the Windows GitHub client and the GitHub Desktop client with GitLab, BitBucket or any other hosted Git solution. \nWe only use it with HTTPS and you'll need a valid certificate if you do use HTTPS. It may work with HTTP as well. We never did get SSH to work completely right since it's a tough to inject your own SSH keys into the application.\nIf you want to clone a repository, you have to drag and drop the HTTP URL onto the GitHub application. \nI was unable to get the drag and drop trick to work on OS X. But you can add locally cloned repositories into the OSX version and then the application works like normal. And OSX supports SSH keys unlike the Windows version." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git - the stupid content tracker git-read-tree" }, { "role": "assistant", "content": "Reads tree information into the index" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How do you remove an invalid remote branch reference from Git?\nIn my current repo I have the following output:\n$ git branch -a\n* master\n remotes/origin/master\n remotes/public/master\n\nI want to delete remotes/public/master from the branch list:\n$ git branch -d remotes/public/master\nerror: branch 'remotes/public/master' not found.\n\nAlso, the output of git remote is strange, since it does not list public:\n$ git remote show \norigin\n\nHow can I delete 'remotes/public/master' from the branch list?\nUpdate, tried the git push command:\n$ git push public :master\nfatal: 'public' does not appear to be a git repository\nfatal: The remote end hung up unexpectedly" }, { "role": "assistant", "content": "You might be needing a cleanup:\ngit gc --prune=now\n\nor you might be needing a prune:\ngit remote prune public\n\n\nprune\nDeletes all stale tracking branches under <name>. These stale branches have already been removed from the remote repository referenced by <name>, but are still locally available in \"remotes/<name>\".\nWith --dry-run option, report what branches will be pruned, but do no actually prune them.\n\nHowever, it appears these should have been cleaned up earlier with \ngit remote rm public \n\n\nrm\nRemove the remote named <name>. All remote tracking branches and configuration settings for the remote\n are removed.\n\nSo it might be you hand-edited your config file and this did not occur, or you have privilege problems.\nMaybe run that again and see what happens.\n\nAdvice Context\nIf you take a look in the revision logs, you'll note I suggested more \"correct\" techniques, which for whatever reason didn't want to work on their repository. \nI suspected the OP had done something that left their tree in an inconsistent state that caused it to behave a bit strangely, and git gc was required to fix up the left behind cruft.\nUsually git branch -rd origin/badbranch is sufficient for nuking a local tracking branch , or git push origin :badbranch for nuking a remote branch, and usually you will never need to call git gc" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Delete a remote branch with the same name as tag\nI have a branch and a tag by the name 3.0.0. Now how do i only delete the branch not the tag.\nI tried \ngit push origin --delete 3.0.0\nerror: dst refspec 3.0.0 matches more than one." }, { "role": "assistant", "content": "You can push the full branch refspec:\ngit push origin :refs/heads/3.0.0\n# shorter:\ngit push origin :heads/3.0.0\n\ngit push --delete refs/heads/3.0.0\n# shorter\ngit push -d refs/heads/3.0.0\n\nThat would reference only a branch, not a tag (refs/tags/3.0.0).\nHere the refspec has no source in front of the ':': that means deletion.\n\nBecause the refspec is <src>:<dst>, by leaving off the <src> part, this basically says to make the topic branch on the remote \"nothing\", which deletes it.\n\nI mentioned the alternative --delete syntax here: git push -d." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "What does \"Auto packing the repository for optimum performance\" mean?\nI'm having a problem with my git repo. For the last couple of days whenever I do a push to the server I get this message: \"Auto packing the repository for optimum performance\", and it does not seem to go away and return the shell.\nI also tried checking out to a new branch and then doing a rebase on my previous branch and then did git gc to remove the unused history objects and then did a push but still this message appears. Please let me know what's going on with my repo." }, { "role": "assistant", "content": "Short version: it means what it says, and if you just let it finish, all will be well.\nDuring most operations which can potentially increase the number of loose (unpacked) objects in the repository (including pushes), Git invokes git gc --auto. If there are enough loose objects (by default, at least 6700), it will then invoke git repack -d -l to pack them. If there are too many separate packs, it will also repack them into one.\nA pack is a delta-compressed single file, containing a large number of objects. It's more efficient to store objects in packs, but it takes time to pack (compress) objects, so Git initially creates loose objects, then packs them in batches now and then, via automatic invocation of git gc --auto.\nIf you let Git finish repacking, this won't happen again for a while. It can indeed take a while, especially if you have a lot of large binary objects, but if it's triggering, then it's a sign that it will probably drastically reduce the amount of disk space taken by the repo. If you really don't want it to happen, you can change the config parameter gc.auto. If you increase it to something much larger than 6700, it will happen less frequently, but take longer when it does. If you decrease it, it'll still have to do your current repack, but subsequently it will happen more often and finish more quickly. If you set it to 0, it will disable automatic repacking.\nSee man git-gc (under --auto) and man git-config (under gc.auto) for more information." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How to find out in which commit a particular code was added?\nI want to find out in which commit did I add the code given below: \nif (getListView().getChildCount() == 0)\n getActivity().findViewById(android.R.id.empty).setVisibility(View.VISIBLE);\n\nHow do I achieve this?" }, { "role": "assistant", "content": "git log -S searchTerm\n\ngives you the commits in which the search term was introduced." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-log - Show commit logs -O<orderfile>" }, { "role": "assistant", "content": "Control the order in which files appear in the output.\nThis overrides the diff.orderFile configuration variable\n(see git-config ). To cancel diff.orderFile ,\nuse -O/dev/null . The output order is determined by the order of glob patterns in\n<orderfile>.\nAll files with pathnames that match the first pattern are output\nfirst, all files with pathnames that match the second pattern (but not\nthe first) are output next, and so on.\nAll files with pathnames that do not match any pattern are output\nlast, as if there was an implicit match-all pattern at the end of the\nfile.\nIf multiple pathnames have the same rank (they match the same pattern\nbut no earlier patterns), their output order relative to each other is\nthe normal order. <orderfile> is parsed as follows: Blank lines are ignored, so they can be used as separators for\nreadability. Lines starting with a hash (\" # \") are ignored, so they can be used\nfor comments. Add a backslash (\" \\ \") to the beginning of the\npattern if it starts with a hash. Each other line contains a single pattern. Patterns have the same syntax and semantics as patterns used for\nfnmatch(3) without the FNM_PATHNAME flag, except a pathname also\nmatches a pattern if removing any number of the final pathname\ncomponents matches the pattern. For example, the pattern \" foo*bar \"\nmatches \" fooasdfbar \" and \" foo/bar/baz/asdf \" but not \" foobarx \"." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-config - Get and set repository or global options mailmap.blob" }, { "role": "assistant", "content": "Like mailmap.file , but consider the value as a reference to a\nblob in the repository. If both mailmap.file and mailmap.blob are given, both are parsed, with entries from mailmap.file taking precedence. In a bare repository, this\ndefaults to HEAD:.mailmap . In a non-bare repository, it\ndefaults to empty." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-svn - Bidirectional operation between a Subversion repository and Git --ignore-refs=<regex>" }, { "role": "assistant", "content": "Ignore refs for branches or tags matching the Perl regular\nexpression. A \"negative look-ahead assertion\" like ^refs/remotes/origin/(?!tags/wanted-tag\|wanted-branch).*$ can be used to allow only certain refs. config key: svn-remote.<name>.ignore-refs If the ignore-refs configuration key is set, and the command-line\noption is also given, both regular expressions will be used." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Exceptions in .gitignore [duplicate]\nThis question already has answers here:\n \n \n\n\n\n\nMake .gitignore ignore everything except a few files\n\n (30 answers)\n \n\nClosed 4 years ago.\n\n\n\nHow can I add an exception to .gitignore, like \"ignore all the .dll files BUT myfile.dll\"?" }, { "role": "assistant", "content": "Use ! to negate the pattern:\n*.dll\n!myfile.dll" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How to display HTML content in github README.md?\n\nI am new to github, in README.md want to display a HTML content using an Iframe or something is this possible ? \nWhat I have tried is I just create HTML tags other then anchor, that is not working." }, { "role": "assistant", "content": "Github's markdown interpreter can include HTML. However, there is only so much you can do in HTML. I would suggest checking out this article which provides more information on what tags can be used. Personally, I have never used much more than line-breaks, horizontal rules, etc... Unfortunately, I don't see Iframes mentioned in the article." } ]
[ { "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": "GitLab: How to embed image from repo in the wiki?\n\nI have a GitLab repository with documentation in the attached wiki (i.e. NOT in the repo itself) and an image file inside the repository itself that I want to embed in wiki pages.\nHow can this be done?\nFrom a wiki page, I can successfully link to the image using\n[[../tree/master/pathto/myimage.jpg]] or [[../raw/master/pathto/myimage.jpg]] but \n\n![](../raw/master/pathto/myimage.jpg)\n \ndoesn't seem to work.\n(GitLab Community Edition 10.0.3)" }, { "role": "assistant", "content": "Embedding using the absolute path to the repo and image worked:\n![](https://url.of.my.repo/raw/master/pathto/myimage.jpg)" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "gitfaq - Frequently asked questions about using Git" }, { "role": "assistant", "content": "DESCRIPTION The examples in this FAQ assume a standard POSIX shell, like bash or dash ,\nand a user, A U Thor, who has the account author on the hosting provider git.example.org ." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Github: Mirroring gh-pages to master\n\nI'm developing a jQuery plugin that's being hosting on GitHub. It has a demo included of which I'm manually copying and pushing to the branch gh-pages, what I'd like to do is have it so when I push a change to master it is automatically pushed to gh-pages, or at least a setup where they are mirrored.\nI've already seen this question but not sure if it really answers my question with regard to these requirements:\n\nI use Tower, I don't mind using the terminal (Mac) to make changes to config, so long as the solution works with this GUI.\nI only want this 'mirroring' on certain repos, not on all of them on my machine.\n\nCheers" }, { "role": "assistant", "content": "Add the following 2 lines to the [remote \"origin\"] section of .git/config:\npush = +refs/heads/master:refs/heads/gh-pages\npush = +refs/heads/master:refs/heads/master\n\nEvery time you push it will automatically push master to gh-pages as well.\nI'm using this for the jQuery Lifestream project." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git - the stupid content tracker git-init" }, { "role": "assistant", "content": "Create an empty Git repository or reinitialize an existing one" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "gitworkflows - An overview of recommended workflows with Git" }, { "role": "assistant", "content": "MANAGING BRANCHES There are two main tools that can be used to include changes from one\nbranch on another: git-merge and git-cherry-pick . Merges have many advantages, so we try to solve as many problems as\npossible with merges alone. Cherry-picking is still occasionally\nuseful; see \"Merging upwards\" below for an example. Most importantly, merging works at the branch level, while\ncherry-picking works at the commit level. This means that a merge can\ncarry over the changes from 1, 10, or 1000 commits with equal ease,\nwhich in turn means the workflow scales much better to a large number\nof contributors (and contributions). Merges are also easier to\nunderstand because a merge commit is a \"promise\" that all changes from\nall its parents are now included. There is a tradeoff of course: merges require a more careful branch\nmanagement. The following subsections discuss the important points. Graduation As a given feature goes from experimental to stable, it also\n\"graduates\" between the corresponding branches of the software. git.git uses the following integration branches : maint tracks the commits that should go into the next \"maintenance\nrelease\", i.e., update of the last released stable version; master tracks the commits that should go into the next release; next is intended as a testing branch for topics being tested for\nstability for master. There is a fourth official branch that is used slightly differently: seen (patches seen by the maintainer) is an integration branch for\nthings that are not quite ready for inclusion yet (see \"Integration\nBranches\" below). Each of the four branches is usually a direct descendant of the one\nabove it. Conceptually, the feature enters at an unstable branch (usually next or seen ), and \"graduates\" to master for the next release once it is\nconsidered stable enough. Merging upwards The \"downwards graduation\" discussed above cannot be done by actually\nmerging downwards, however, since that would merge all changes on\nthe unstable branch into the stable one. Hence the following: Rule: Merge upwards Always commit your fixes to the oldest supported branch that requires\nthem. Then (periodically) merge the integration branches upwards into each\nother. This gives a very controlled flow of fixes. If you notice that you\nhave applied a fix to e.g. master that is also required in maint ,\nyou will need to cherry-pick it (using git-cherry-pick )\ndownwards. This will happen a few times and is nothing to worry about\nunless you do it very frequently. Topic branches Any nontrivial feature will require several patches to implement, and\nmay get extra bugfixes or improvements during its lifetime. Committing everything directly on the integration branches leads to many\nproblems: Bad commits cannot be undone, so they must be reverted one\nby one, which creates confusing histories and further error potential\nwhen you forget to revert part of a group of changes. Working in\nparallel mixes up the changes, creating further confusion. Use of \"topic branches\" solves these problems. The name is pretty\nself explanatory, with a caveat that comes from the \"merge upwards\"\nrule above: Rule: Topic branches Make a side branch for every topic (feature, bugfix, …). Fork it off\nat the oldest integration branch that you will eventually want to merge it\ninto. Many things can then be done very naturally: To get the feature/bugfix into an integration branch, simply merge\nit. If the topic has evolved further in the meantime, merge again.\n(Note that you do not necessarily have to merge it to the oldest\nintegration branch first. For example, you can first merge a bugfix\nto next , give it some testing time, and merge to maint when you\nknow it is stable.) If you find you need new features from the branch other to continue\nworking on your topic, merge other to topic . (However, do not\ndo this \"just habitually\", see below.) If you find you forked off the wrong branch and want to move it\n\"back in time\", use git-rebase . Note that the last point clashes with the other two: a topic that has\nbeen merged elsewhere should not be rebased. See the section on\nRECOVERING FROM UPSTREAM REBASE in git-rebase . We should point out that \"habitually\" (regularly for no real reason)\nmerging an integration branch into your topics — and by extension,\nmerging anything upstream into anything downstream on a regular basis — is frowned upon: Rule: Merge to downstream only at well-defined points Do not merge to downstream except with a good reason: upstream API\nchanges affect your branch; your branch no longer merges to upstream\ncleanly; etc. Otherwise, the topic that was merged to suddenly contains more than a\nsingle (well-separated) change. The many resulting small merges will\ngreatly clutter up history. Anyone who later investigates the history\nof a file will have to find out whether that merge affected the topic\nin development. An upstream might even inadvertently be merged into a\n\"more stable\" branch. And so on. Throw-away integration If you followed the last paragraph, you will now have many small topic\nbranches, and occasionally wonder how they interact. Perhaps the\nresult of merging them does not even work? But on the other hand, we\nwant to avoid merging them anywhere \"stable\" because such merges\ncannot easily be undone. The solution, of course, is to make a merge that we can undo: merge\ninto a throw-away branch. Rule: Throw-away integration branches To test the interaction of several topics, merge them into a\nthrow-away branch. You must never base any work on such a branch! If you make it (very) clear that this branch is going to be deleted\nright after the testing, you can even publish this branch, for example\nto give the testers a chance to work with it, or other developers a\nchance to see if their in-progress work will be compatible. git.git has such an official throw-away integration branch called seen . Branch management for a release Assuming you are using the merge approach discussed above, when you\nare releasing your project you will need to do some additional branch\nmanagement work. A feature release is created from the master branch, since master tracks the commits that should go into the next feature release. The master branch is supposed to be a superset of maint . If this\ncondition does not hold, then maint contains some commits that\nare not included on master . The fixes represented by those commits\nwill therefore not be included in your feature release. To verify that master is indeed a superset of maint , use git log: Recipe: Verify master is a superset of maint git log master..maint This command should not list any commits. Otherwise, check out master and merge maint into it. Now you can proceed with the creation of the feature release. Apply a\ntag to the tip of master indicating the release version: Recipe: Release tagging git tag -s -m \"Git X.Y.Z\" vX.Y.Z master You need to push the new tag to a public Git server (see\n\"DISTRIBUTED WORKFLOWS\" below). This makes the tag available to\nothers tracking your project. The push could also trigger a\npost-update hook to perform release-related items such as building\nrelease tarballs and preformatted documentation pages. Similarly, for a maintenance release, maint is tracking the commits\nto be released. Therefore, in the steps above simply tag and push maint rather than master . Maintenance branch management after a feature release After a feature release, you need to manage your maintenance branches. First, if you wish to continue to release maintenance fixes for the\nfeature release made before the recent one, then you must create\nanother branch to track commits for that previous release. To do this, the current maintenance branch is copied to another branch\nnamed with the previous release version number (e.g. maint-X.Y.(Z-1)\nwhere X.Y.Z is the current release). Recipe: Copy maint git branch maint-X.Y.(Z-1) maint The maint branch should now be fast-forwarded to the newly released\ncode so that maintenance fixes can be tracked for the current release: Recipe: Update maint to new release git checkout maint git merge --ff-only master If the merge fails because it is not a fast-forward, then it is\npossible some fixes on maint were missed in the feature release.\nThis will not happen if the content of the branches was verified as\ndescribed in the previous section. Branch management for next and seen after a feature release After a feature release, the integration branch next may optionally be\nrewound and rebuilt from the tip of master using the surviving\ntopics on next : Recipe: Rewind and rebuild next git switch -C next master git merge ai/topic_in_next1 git merge ai/topic_in_next2 … The advantage of doing this is that the history of next will be\nclean. For example, some topics merged into next may have initially\nlooked promising, but were later found to be undesirable or premature.\nIn such a case, the topic is reverted out of next but the fact\nremains in the history that it was once merged and reverted. By\nrecreating next , you give another incarnation of such topics a clean\nslate to retry, and a feature release is a good point in history to do\nso. If you do this, then you should make a public announcement indicating\nthat next was rewound and rebuilt. The same rewind and rebuild process may be followed for seen . A public\nannouncement is not necessary since seen is a throw-away branch, as\ndescribed above." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How to run Gitlab CI only for specific branches and tags?\n\nI would like to setup my project_dev CI only for 3 branches and specific kind of tags like: dev_1.0, dev_1.1, dev_1.2.\nHow can I achieve that?\nThis is what I have now:\n\nproject_dev:\n stage: dev\n script:\n - export\n - bundle exec pod repo update\n - bundle exec pod install\n - bundle exec fastlane crashlytics_project_dev\n after_script:\n - rm -rf ~/Library/Developer/Xcode/Archives \|\| true\n when: manual\n only:\n - develop\n - release\n - master\n - //here I need to add condition to fire that stage additionally only for specific tags. How can I setup regexp here?\n tags:\n - iOS\n\nWhen I type it like:\n\n only:\n - branches\n - /^dev_[0-9.]*$/\n\nIt also runs the CI for tags like: dev1.2 but it should not. Why? Is there a regexp for tags at all?" }, { "role": "assistant", "content": "Sounds like a regular expression question. I just created a project on gitlab.com for the regular expression.\nFile: .gitlab-ci.yml\nproject_dev:\n # Irrelevant keys is skipped\n script:\n - echo \"Hello World\"\n only:\n - develop\n - release\n - master\n - /^dev_[0-9]+(?:.[0-9]+)+$/ # regular expression\n\nI was pushed all of tags you mentioned to test this regular expression.\n\nAs you can see , It will match tags like dev_1.0, dev_1.1, but the job project_dev will not be triggered by tag dev1.2, You can check the result on pipeline pages" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Gradle script to autoversion and include the commit hash in Android\nI need to write a gradle script to auto version my application on every commit. I need to also include the commit hash as a reference in the application for testers.\nI am confused how auto versioning usually work. Can someone explain the autoversioning process?" }, { "role": "assistant", "content": "I encountered a similar problem, but did not want to modify the versionName to include the git hash. We wanted to keep that as something like 1.2.2, but still have the possibility of displaying the git hash in the UI. \nI modified the code from the other answer here to use the buildConfigField task to generate a BuildConfig.GitHash value that can be referenced in the Java code.\nAdd this above the android section of your module's build.gradle file:\ndef getGitHash = { ->\n def stdout = new ByteArrayOutputStream()\n exec {\n commandLine 'git', 'rev-parse', '--short', 'HEAD'\n standardOutput = stdout\n }\n return stdout.toString().trim()\n}\n\nThen add the following line to the defaultConfig section of the android section of the build.gradle, i.e. below versionName:\nbuildConfigField \"String\", \"GitHash\", \"\\\"${getGitHash()}\\\"\"\n\nThis generates the following line in the auto-generated BuildConfig.java file:\n// Fields from default config.\npublic static final String GitHash = \"e61af97\";\n\nNow you can get the git hash in your Java code with BuildConfig.GitHash." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "githooks - Hooks used by Git GIT_SENDEMAIL_FILE_TOTAL" }, { "role": "assistant", "content": "The total number of files that will be sent (excluding any FIFOs). This\ncounter does not follow the patch series counter scheme. It will always\nbe equal to the number of files being sent, whether there is a cover\nletter or not." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-config - Get and set repository or global options fetch.bundleCreationToken" }, { "role": "assistant", "content": "When using fetch.bundleURI to fetch incrementally from a bundle\nlist that uses the \"creationToken\" heuristic, this config value\nstores the maximum creationToken value of the downloaded bundles.\nThis value is used to prevent downloading bundles in the future\nif the advertised creationToken is not strictly larger than this\nvalue. The creation token values are chosen by the provider serving the specific\nbundle URI. If you modify the URI at fetch.bundleURI , then be sure to\nremove the value for the fetch.bundleCreationToken value before fetching." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Adding a remote git repo through intelliJ\nI want to know how to add a remote git repo via intelliJ, not through the git bash. Now, from what I've seen in this tutorial, it can be done, but whenever I try to push, the dialogue never comes up. If you push to the very bottom, you can see that it can be done in probably a previous version of IntelliJ. How can you do it with version 12 or rather PyCharm 2.6?" }, { "role": "assistant", "content": "UPDATE: this feature is available since 2016.3 version.\nVCS \| Git \| Remotes \| Add (Alt+Insert).\n\n\nOriginal answer:\nYou can choose from the existing remotes, but you can't add new remotes from the UI, there is a feature request:\n\nIDEA-87099 Provide ability to add remote repositories to local git repository\n\nThe workaround, for those new to Git is to use the commandline and add a remote like so:\ngit remote add remoteName remoteUrl\n\nAfter that, the remote will show up in the pull dialog in Intellij, but it won't show any branches until you do a fetch, like so:\ngit fetch remoteName" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Undo a git rerere resolution that was done in a rebase\nOkay, so I really like the git rerere command, although I haven't really used it that much other than letting it auto-magically record my conflicts and resolve them for me. However, I did mess up one of my conflict resolutions during quite a large rebase (rebasing a really stale feature branch with the latest release).\nfeature -> a - b - c - d\n\nrelease -> e - f - g - h\n\nrebase/feature -> e - f - g - h .\n ` a' - b' - c' - d'\n\nSo, say for instance that b' has an incorrect merge (thanks to me!), and I want to re-record that. How would I do it? I've seen the git checkout --conflict option, mentioned in Rerere Your Boat, but I'm not too clear on how that works and if it applies here. Maybe I have to checkout the merge conflict state and run git rerere once I correctly resolve this conflict?\nNormally, I would just commit to the tip of the rebase branch, but it is a throw away. I'm just trying to handle conflicts ahead of time, so that when I sync up with that feature team, we minimize the time it takes. Make sense?" }, { "role": "assistant", "content": "To simply remove all previous rerere resolutions, run rm -rf .git/rr-cache to remove the cache.\nFor a specific merge, you can tell rerere to forget the recorded resolution by re-executing the merge and allowing rerere to apply its recorded resolution in the work tree.\nYou can check out a' and then do a git merge b to get back into that situation (you'll probably be in a checkout of a detached head since you specified the commit hash of a', so be aware that you're not on a branch).\nThen use git rerere forget FILE-WITH-BAD-MERGE where to specify the file whose recorded conflict resolution should be forgetten.\n\nforget <pathspec>\n Reset the conflict resolutions which rerere has recorded for the current conflict in .\n\n(From the Git documentation for git-rerere.)" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-show - Show various types of objects %GS" }, { "role": "assistant", "content": "show the name of the signer for a signed commit" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Best workflow when forking and renaming a GitHub project [closed]\n\nClosed. This question is opinion-based. 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 can be answered with facts and citations by editing this post.\n\n\nClosed 9 years ago.\n\n\n\n\n\n\n\n Improve this question\n \n\n\n\nI am trying to figure out the best workflow for working with a fork of an existing opensource project in Github. I want to take an existing project and make significant changes to it, in this case to port it to android and add specific android only functionality. I would like to satisfy the following:\n\nBe able to pull changes from their public repo to the new android port as the original code is updated.\nBe able to sumbit changes (via pull requests) to the orginal project when I fix bugs that aren't just applicable to the android port.\nHave a seperate renamed version of the project to make it clear that it is a Android port. I looked at renaming a fork and Github gave me huge warnings about doing this.\n\nMy initial thoughts are I would fork the original project then fork and rename my fork to give me the following repos:\noriginal-author/projectA\nnicstrong/projectA\nnicstrong/projectA-android\n\nThis would allow me to work on my local repo local/projectA-android push changes to nicstrong/projectA-android. Then to update from the orginal project I could rebase nicstrong/projectA to the latest from original-author/projectA then fetch/merge from nicstrong/projectA to local/projectA-android.\nMy questions are:\n\nI am quite new to the whole Git\nthing. Does this seem like a good\napproach? Or is there a better\nworkflow for handling this scenerio?\nHow would I handle pushing from\nprojectA-android back to nicstrong/projectA so I can setup pull request for the original project?" }, { "role": "assistant", "content": "2011:\n1/ Yes, that seems the safest approach, as any modification you end up back-porting in nicstrong/projectA will be in a project with the same structure as original-author/projectA.\nThat means pull requests will be easier to organize, since you will be in a project mirroring the original author's project.\n2/ If you have massive refactoring going on in nicstrong/projectA-android, I would make a backport branch, carefully merge or cherry-pick what you need from the numerous changes to the backport branch, and then push that branch to nicstrong/projectA.\n(which means you have added nicstrong/projectA as a remote of nicstrong/projectA-android)\n\n2022: Note that you can create a fork directly with a different name." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How do I check my github settings or who I'm signed in as on my current project through the terminal?\n\nMy friend set up my github for me and cloned a project onto my desktop. I want to see what is my profile name on the Github account he gave me. Is there a command to do that?" }, { "role": "assistant", "content": "You can see the current configurations, including username, with git config -l.\nYou'll want to look for user.name, user.email, and github.user. \nYou can unset configurations using --unset, like git config user.name --unset. \nYou can also reset configurations using git config user.name \"Your Name\"." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Show both staged & working tree in git diff?\nIf I run git diff I see the changes in my working tree, and if I run git diff --staged (alternatively --cached) then I see the changes that are staged (w/ git add) but is there a way with git diff to see all in one go?" }, { "role": "assistant", "content": "If you mean the changes between the working tree and your HEAD commit (i.e. both staged and unstaged changes together) this is just done with:\ngit diff HEAD" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git - the stupid content tracker git-range-diff" }, { "role": "assistant", "content": "Compare two commit ranges (e.g. two versions of a branch)" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-diff - Show changes between commits, commit and working tree, etc --quiet" }, { "role": "assistant", "content": "Disable all output of the program. Implies --exit-code ." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-instaweb - Instantly browse your working repository in gitweb restart --restart" }, { "role": "assistant", "content": "Restart the httpd instance and exit. Regenerate configuration files\nas necessary for spawning a new instance." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-config - Get and set repository or global options color.grep" }, { "role": "assistant", "content": "When set to always , always highlight matches. When false (or never ), never. When set to true or auto , use color only\nwhen the output is written to the terminal. If unset, then the\nvalue of color.ui is used ( auto by default)." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How can I clone a private GitLab repository?\nWhen I do this:\ngit clone https://example.com/root/test.git\n\nI am getting this error:\n\nfatal: HTTP request failed\n\nWhen I use SSH:\ngit clone username [email protected]:root/test.git\n\nI am getting this error:\n\nInitialized empty Git repository in /server/user/[email protected]:root/test.git/.git/ \n fatal: 'user' does not appear to be a git repository \n fatal: The remote end hung up unexpectedly\n\nIt's a private repository, and I have added my SSH keys." }, { "role": "assistant", "content": "It looks like there's not a straightforward solution for HTTPS-based cloning regarding GitLab. Therefore if you want a SSH-based cloning, you should take account these three forthcoming steps:\n\nCreate properly an SSH key using your email used to sign up. I would use the default filename to key for Windows. Don't forget to introduce a password! (tip: you can skip this step if you already have one ssh key here)\n $ ssh-keygen -t rsa -C \"[email protected]\" -b 4096\n\n Generating public/private rsa key pair.\n Enter file in which to save the key ($PWD/.ssh/id_rsa): [\\n]\n Enter passphrase (empty for no passphrase):[your password]\n Enter same passphrase again: [your password]\n Your identification has been saved in $PWD/.ssh/id_rsa.\n Your public key has been saved in $PWD/.ssh/id_rsa.pub.\n\n\nCopy and paste all content from the recently id_rsa.pub generated into Setting>SSH keys>Key from your GitLab profile.\n # Copy to clipboard\n pbcopy < ~/.ssh/id_rsa.pub\n\n\nGet locally connected:\n $ ssh -i $PWD/.ssh/id_rsa [email protected]\n\n Enter passphrase for key \"$PWD/.ssh/id_rsa\": [your password]\n PTY allocation request failed on channel 0\n Welcome to GitLab, you!\n Connection to gitlab.com closed.\n\n\n\nFinally, clone any private or internal GitLab repository!\n$ git clone https://git.metabarcoding.org/obitools/ROBIBarcodes.git\n\nCloning into 'ROBIBarcodes'...\nremote: Counting objects: 69, done.\nremote: Compressing objects: 100% (65/65), done.\nremote: Total 69 (delta 14), reused 0 (delta 0)\nUnpacking objects: 100% (69/69), done." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git - the stupid content tracker" }, { "role": "assistant", "content": "Configuration Mechanism Git uses a simple text format to store customizations that are per\nrepository and are per user. Such a configuration file may look\nlike this: #\n# A '#' or ';' character indicates a comment.\n#\n\n; core variables\n[core]\n\t; Don't trust file modes\n\tfilemode = false\n\n; user identity\n[user]\n\tname = \"Junio C Hamano\"\n\temail = \"gitster@pobox.com\" Various commands read from the configuration file and adjust\ntheir operation accordingly. See git-config for a\nlist and more details about the configuration mechanism." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Git: Cannot see new remote branch\nA colleague pushed a new remote branch to origin/dev/homepage and I cannot see it when I run:\n$ git branch -r\n\nI still see preexisting remote branches. \nI assume this is because my local remote refs are not up-to-date hence when I ran a git pull nothing happened since git pull only pulls on the current working branch correct? Unlike git push which pushes all branches that have changes to the corresponding remote branch?" }, { "role": "assistant", "content": "First, double check that the branch has been actually pushed remotely, by using the command git ls-remote origin. If the new branch appears in the output, try and give the command git fetch: it should download the branch references from the remote repository.\nIf your remote branch still does not appear, double check (in the ls-remote output) what is the branch name on the remote and, specifically, if it begins with refs/heads/. This is because, by default, the value of remote.<name>.fetch is:\n+refs/heads/:refs/remotes/origin/\n\nso that only the remote references whose name starts with refs/heads/ will be mapped locally as remote-tracking references under refs/remotes/origin/ (i.e., they will become remote-tracking branches)" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Is there a way to cache https credentials for pushing commits?\n\nI recently switched to synchronizing my repositories to https:// on GitHub (due to firewall issues), and it asks for a password every time.\nIs there a way to cache the credentials, instead of authenticating every time that git push?" }, { "role": "assistant", "content": "Since Git 1.7.9 (released 2012), there is a neat mechanism in Git to avoid having to type your password all the time for HTTP / HTTPS, called credential helpers.\nYou can just use one of the following credential helpers:\ngit config --global credential.helper cache\n\nThe credential.helper cache value tells Git to keep your password cached in memory for a particular amount of minutes. The default is 15 minutes, you can set a longer timeout with:\n# Cache for 1 hour\ngit config --global credential.helper \"cache --timeout=3600\"\n\n# Cache for 1 day\ngit config --global credential.helper \"cache --timeout=86400\"\n\n# Cache for 1 week\ngit config --global credential.helper \"cache --timeout=604800\"\n\nYou can also store your credentials permanently if so desired, see the other answers below.\nGitHub's help also suggests that if you're on Mac OS X and used Homebrew to install Git, you can use the native Mac OS X keystore with:\ngit config --global credential.helper osxkeychain\n\nFor Windows, there is a helper called Git Credential Manager for Windows or wincred in msysgit.\ngit config --global credential.helper wincred # obsolete\n\nWith Git for Windows 2.7.3+ (March 2016):\ngit config --global credential.helper manager\n\nFor Linux, you would use (in 2011) gnome-keyring(or other keyring implementation such as KWallet).\nNowadays (2020), that would be (on Linux)\nFedora\nsudo dnf install git-credential-libsecret\ngit config --global credential.helper /usr/libexec/git-core/git-credential-libsecret\n\nUbuntu\nsudo apt-get install libsecret-1-0 libsecret-1-dev\ncd /usr/share/doc/git/contrib/credential/libsecret\nsudo make\ngit config --global credential.helper /usr/share/doc/git/contrib/credential/libsecret/git-credential-libsecret" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-log - Show commit logs --relative-date" }, { "role": "assistant", "content": "Synonym for --date=relative ." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Can I use a GitHub project directly in Maven?\n\nI am interested in using a project on GitHub as a dependency in my project. The GitHub project has a pom file. Can I modify my pom file to use this project? If so, how? If not, what is my best course of action?" }, { "role": "assistant", "content": "Try jitpack, you just need to add the dependency, jitpack will build others for you.\nFrom home page:\n\njitpack\n Easy to use package repository for Gradle and Maven projects\n JitPack builds GitHub projects on demand and provides ready-to-use packages\n\nHOW\n\nAdd repository first\n\n<repository>\n <id>jitpack.io</id>\n <url>https://jitpack.io</url>\n</repository>\n\n\nAdd dependency\n\n<dependency>\n <groupId>com.github.User</groupId>\n <artifactId>Repo name</artifactId>\n <version>Release tag</version>\n</dependency>\n\nTIPS:\nYou can see its build log too https://jitpack.io/com/github/NanoHttpd/nanohttpd/Release-2.1.0/build.log" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-commit-tree - Create a new commit object -m <message>" }, { "role": "assistant", "content": "A paragraph in the commit log message. This can be given more than\nonce and each <message> becomes its own paragraph." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How to merge two GitHub accounts\n\nI have two GitHub accounts, one of this was created a long time ago at my work and has an username that refers to the company where I work.\nI have another account which is my personal GitHub account that I can't stop using. \nCould I merge the two accounts so I can work in only one of these?" }, { "role": "assistant", "content": "Merging 2 accounts is not possible at github, you can transfer ownership to your personal account.\ngoto >> Setting >>Transfer ownership \n\nFor more details : https://help.github.com/articles/merging-multiple-user-accounts/" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Git is really slow for 100,000 objects. Any fixes?\nI have a \"fresh\" git-svn repo (11.13 GB) that has over a 100,000 objects in it.\nI have preformed\ngit fsck\ngit gc\n\non the repo after the initial checkout.\nI then tried to do a\ngit status\n\nThe time it takes to do a git status is anywhere from 2m25.578s and 2m53.901s\nI tested git status by issuing the command\ntime git status\n\n5 times and all of the times ran between the two times listed above.\nI am doing this on a Mac OS X, locally not through a VM.\nThere is no way it should be taking this long.\nAny ideas? Help?\nThanks.\nEdit\nI have a co-worker sitting right next to me with a comparable box. Less RAM and running Debian with a jfs filesystem. His git status runs in .3 on the same repo (it is also a git-svn checkout).\nAlso, I recently changed my file permissions (to 777) on this folder and it brought the time down considerably (why, I have no clue). I can now get it done anywhere between 3 and 6 seconds. This is manageable, but still a pain." }, { "role": "assistant", "content": "It came down to a couple of items that I can see right now.\n\ngit gc --aggressive\nOpening up file permissions to 777\n\nThere has to be something else going on, but this was the things that clearly made the biggest impact." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How to exit git log or git diff [duplicate]\nThis question already has answers here:\n \n \n\n\n\n\nHow to exit a 'git status' list in a terminal?\n\n (17 answers)\n \n\nClosed 8 years ago.\n\n\n\nI'm trying to learn Git with the help of Git Immersion.\nThere's one thing that frustrates me whenever I use git log or git diff:\n\nI can't figure out what to do next when I encounter this (END) word.\nI can't type any commands, and I end up closing the current Bash window and open another. How do I type in the next command that I want to use?" }, { "role": "assistant", "content": "You're in the less program, which makes the output of git log scrollable.\nType q to exit this screen. Type h to get help.\nIf you don't want to read the output in a pager and want it to be just printed to the terminal define the environment variable GIT_PAGER to cat or set core.pager to cat (execute git config --global core.pager cat)." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git - the stupid content tracker gitformat-signature" }, { "role": "assistant", "content": "Git cryptographic signature formats" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-fetch - Download objects and refs from another repository" }, { "role": "assistant", "content": "DESCRIPTION Fetch branches and/or tags (collectively, \"refs\") from one or more\nother repositories, along with the objects necessary to complete their\nhistories. Remote-tracking branches are updated (see the description\nof <refspec> below for ways to control this behavior). By default, any tag that points into the histories being fetched is\nalso fetched; the effect is to fetch tags that\npoint at branches that you are interested in. This default behavior\ncan be changed by using the --tags or --no-tags options or by\nconfiguring remote.<name>.tagOpt. By using a refspec that fetches tags\nexplicitly, you can fetch tags that do not point into branches you\nare interested in as well. git fetch can fetch from either a single named repository or URL,\nor from several repositories at once if <group> is given and\nthere is a remotes.<group> entry in the configuration file.\n(See git-config ). When no remote is specified, by default the origin remote will be used,\nunless there’s an upstream branch configured for the current branch. The names of refs that are fetched, together with the object names\nthey point at, are written to .git/FETCH_HEAD . This information\nmay be used by scripts or other git commands, such as git-pull ." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Issue with adding common code as git submodule: \"already exists in the index\"\nI want to add some git submodules.\nI've received two projects sharing some common code. The shared code was just copied into the two projects. I created a separate git repo for the common code and removed it from the projects with the plan to add it as a git submodule.\nI used the path option of git submodule add to specify the folder:\ngit submodule add url_to_repo projectfolder\n\nbut then got the error:\n'projectfolder' already exists in the index\"\n\nThis is the desired structure of my repository:\nrepo\n\|-- projectfolder\n \|-- folder with common code\n\nIt is possible to add the git submodule directly in the repo, or into a new folder there, but not in the project folder. The problem is that it really need to be in the project folder..\nWhat can I do about this and what have I misunderstood about the path option of git submodule add?" }, { "role": "assistant", "content": "I'm afraid there's not enough information in your question to be certain about what's going on, since you haven't replied to my follow-up question, but this may be of help in any case.\nThat error means that projectfolder is already staged (\"already exists in the index\"). To find out what's going on here, try to list everything in the index under that folder with:\ngit ls-files --stage projectfolder\n\nThe first column of that output will tell you what type of object is in the index at projectfolder. (These look like Unix filemodes, but have special meanings in git.)\nI suspect that you will see something like:\n160000 d00cf29f23627fc54eb992dde6a79112677cd86c 0 projectfolder\n\n(i.e. a line beginning with 160000), in which case the repository in projectfolder has already been added as a \"gitlink\". If it doesn't appear in the output of git submodule, and you want to re-add it as a submodule, you can do:\ngit rm --cached projectfolder\n\n... to unstage it, and then:\ngit submodule add url_to_repo projectfolder\n\n... to add the repository as a submodule.\nHowever, it's also possible that you will see many blobs listed (with file modes 100644 and 100755), which would suggest to me that you didn't properly unstage the files in projectfolder before copying the new repository into place. If that's the case, you can do the following to unstage all of those files:\ngit rm -r --cached projectfolder\n\n... and then add the submodule with:\ngit submodule add url_to_repo projectfolder" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-blame - Show what revision and author last modified each line of a file" }, { "role": "assistant", "content": "DESCRIPTION Annotates each line in the given file with information from the revision which\nlast modified the line. Optionally, start annotating from the given revision. When specified one or more times, -L restricts annotation to the requested\nlines. The origin of lines is automatically followed across whole-file\nrenames (currently there is no option to turn the rename-following\noff). To follow lines moved from one file to another, or to follow\nlines that were copied and pasted from another file, etc., see the -C and -M options. The report does not tell you anything about lines which have been deleted or\nreplaced; you need to use a tool such as git diff or the \"pickaxe\"\ninterface briefly mentioned in the following paragraph. Apart from supporting file annotation, Git also supports searching the\ndevelopment history for when a code snippet occurred in a change. This makes it\npossible to track when a code snippet was added to a file, moved or copied\nbetween files, and eventually deleted or replaced. It works by searching for\na text string in the diff. A small example of the pickaxe interface\nthat searches for blame_usage : $ git log --pretty=oneline -S'blame_usage'\n5040f17eba15504bad66b14a645bddd9b015ebb7 blame -S <ancestry-file>\nea4c7f9bf69e781dd0cd88d2bccb2bf5cc15c9a7 git-blame: Make the output" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "What does the \"diff --git\" output in \"git diff\" refer to?\nWhen I run git diff, the output begins with:\ndiff --git a/foo/bar b/foo/bar\n\nIf I try to run plain old diff --git, I'm told that the --git option doesn't exist (obviously, I guess, it would seem silly for a low-level tool to know about a specific DVCS). There's no mention of it in the man page as well. Where does this come from?" }, { "role": "assistant", "content": "It's an \"imaginary diff option\", used to indicate to the reader that it's not just the output of running the diff command. For example, in git's own git repo:\n$ git diff HEAD~1..HEAD \| head\ndiff --git Documentation/git.txt Documentation/git.txt\nindex bd659c4..7913fc2 100644\n--- Documentation/git.txt\n+++ Documentation/git.txt\n@@ -43,6 +43,11 @@ unreleased) version of Git, that is available from the 'master'\n branch of the `git.git` repository.\n Documentation for older releases are available here:\n\n+* link:v2.10.0/git.html[documentation for release 2.10]\n+\n$ \n\nThe diff command itself, if you invoked it with the same file name twice, would show no differences. git presumably creates temporary files corresponding to two different versions of Documentation/git.txt and feeds them to diff -- but the names of those temporary files would not be useful. I think git diff massages the output of diff to make it more meaningful to the reader. (This speculation was not entirely correct. See below.)\nDiving into the git source code, diff.c has the string \"diff --git\" hardwired as a string literal:\nstrbuf_addf(&header, \"%s%sdiff --git %s %s%s\\n\", line_prefix, meta, a_one, b_two, reset);\n\nAnd looking into the history of diff.c for the earliest version that contains that string:\n$ git log -n 1 b58f23b3\ncommit b58f23b38a9a9f28d751311353819d3cdf6a86da\nAuthor: Junio C Hamano <[email protected]>\nDate: 2005-05-18 09:10:47 -0700\n\n [PATCH] Fix diff output take #4.\n\n This implements the output format suggested by Linus in\n <[email protected]>, except the\n imaginary diff option is spelled \"diff --git\" with double dashes as\n suggested by Matthias Urlichs.\n\n Signed-off-by: Junio C Hamano <[email protected]>\n Signed-off-by: Linus Torvalds <[email protected]>\n$ \n\nPresumably <Pine.LNX...> is the message-id of some email message in a mailing list somewhere. In any case, this commit message makes it clear that diff --git is an \"imaginary diff option\".\nThis email message, cited by nos in a comment, appears to be part of the discussion that led to this.\nUPDATE: I speculated above that git diff massages the output of diff, adding this information. I just tried running git diff under strace. It doesn't actually invoke the diff command, or any other command. Rather, all the output is printed by the git process itself, and apparently it computes the differences internally. This behavior might also depend on the version of git (I'm using 2.23.0), the diff command(s) available, and the arguments used.\nI'll note that GNU diff has a --label=LABEL option that could be used for this kind of thing:\n'-L LABEL'\n'--label=LABEL'\n Use LABEL instead of the file name in the context format (note\n Context Format::) and unified format (note Unified Format::)\n headers. *Note RCS::.\n\nbut git diff doesn't use it, at least in the one case I tried, and I don't see a reference to it in the git sources." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "giteveryday - A useful minimum set of commands for Everyday Git Push into another repository." }, { "role": "assistant", "content": "satellite$ git clone mothership:frotz frotz (1) satellite$ cd frotz\nsatellite$ git config --get-regexp '^(remote\|branch)\\.' (2) remote.origin.url mothership:frotz\nremote.origin.fetch refs/heads/:refs/remotes/origin/\nbranch.master.remote origin\nbranch.master.merge refs/heads/master\nsatellite$ git config remote.origin.push \\\n\t +refs/heads/:refs/remotes/satellite/ (3) satellite$ edit/compile/test/commit\nsatellite$ git push origin (4) mothership$ cd frotz\nmothership$ git switch master\nmothership$ git merge satellite/master (5) mothership machine has a frotz repository under your home\ndirectory; clone from it to start a repository on the satellite\nmachine. clone sets these configuration variables by default.\nIt arranges git pull to fetch and store the branches of mothership\nmachine to local remotes/origin/* remote-tracking branches. arrange git push to push all local branches to\ntheir corresponding branch of the mothership machine. push will stash all our work away on remotes/satellite/* remote-tracking branches on the mothership machine. You could use this\nas a back-up method. Likewise, you can pretend that mothership\n\"fetched\" from you (useful when access is one sided). on mothership machine, merge the work done on the satellite\nmachine into the master branch." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Heroku 'Permission denied (publickey) fatal: Could not read from remote repository' woes\nI've searched around for many hours on end looking to a solution to my seemingly easy-to-fix problem. It's not that my search turned up nothing, it's that my search turned up so many different solutions -none of which have worked.\nAnyways, I am simply unable to push, pull, or fetch from my Heroku repository from my Mac. Every attempt gives me (as if it's mocking me) the following error:\n\n'Permission denied (publickey). fatal: Could not read from remote\n repository.'\n\nI've tried (and re-tried) to fix it in many different ways. As I've said, I've spent a good chunk of the last two days searching around for an answer. Here are some of the things I've tried:\n\nheroku keys:clear followed by heroku keys:add\nRegenerating an ssh key on my own with 'ssh-keygen -t rsa'\nClearing out my .ssh directory, followed by heroku keys:clear, followed by generating an ssh key\nDeleting my app on heroku and recreating one (fortunately not much was on there)\n\nI can fetch from my GitHub repository fine, so I know it's not network connectivity (pinging heroku also works). \nAs a makeshift solution (that I hope doesn't turn into a permanent one), I've logged in to my Ubuntu Amazon AWS ec2 instance. Pulling and pushing to and from Heroku works perfectly. For this reason, I still feel as if the problem lies with the ssh key on my Mac. Both keys show up under my Heroku account. Does the email address at the end of the key matter?\nEDIT: I can push and pull from GitHub fine (I'm not using ssh, however), so why not Heroku?\nAt this point I'm willing to try anything. Thanks!" }, { "role": "assistant", "content": "I know this has already been answered. But I would like to add my solution as it may helpful for others in the future..\nA common key error is: Permission denied (publickey). You can fix this by using keys:add to notify Heroku of your new key.\nIn short follow these steps: https://devcenter.heroku.com/articles/keys\nFirst you have to create a key if you don't have one:\nssh-keygen -t rsa\n\nSecond you have to add the key to Heroku:\nheroku keys:add" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-clean - Remove untracked files from the working tree quit" }, { "role": "assistant", "content": "This lets you quit without doing any cleaning." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Found a swap file by the name\n\nWhen I try to merge my branch with a remote branch:\ngit merge feature/remote_branch\n\nI got this message:\nE325: ATTENTION\nFound a swap file by the name \".git/.MERGE_MSG.swp\"\n owned by: xxxxxx dated: Mon Nov 12 23:17:40 2012\n file name: ~xxxxxx/Desktop/My-ios-App/.git/MERGE_MSG\n modified: YES\n user name: xxxxxx host name: unknown-b8-8d-12-22-27-72.lan\n process ID: 1639\nWhile opening file \".git/MERGE_MSG\"\n dated: Tue Nov 13 14:06:48 2012\n NEWER than swap file!\n\n(1) Another program may be editing the same file.\n If this is the case, be careful not to end up with two\n different instances of the same file when making changes.\n Quit, or continue with caution.\n\n(2) An edit session for this file crashed.\n If this is the case, use \":recover\" or \"vim -r .git/MERGE_MSG\"\n to recover the changes (see \":help recovery\").\n If you did this already, delete the swap file \".git/.MERGE_MSG.swp\"\n to avoid this message.\n\nSwap file \".git/.MERGE_MSG.swp\" already exists!\n[O]pen Read-Only, (E)dit anyway, (R)ecover, (D)elete it, (Q)uit, (A)bort:\n\nHow to deal with this?" }, { "role": "assistant", "content": "Looks like you have an open git commit or git merge going on, and an editor is still open editing the commit message.\nTwo choices:\n\nFind the session and finish it (preferable).\nDelete the .swp file (if you're sure the other git session has gone away).\n\nClarification from comments:\n\nThe session is the editing session.\nYou can see what .swp is being used by entering the command :sw within the editing session, but generally it's a hidden file in the same directory as the file you are using, with a .swp file suffix (i.e. ~/myfile.txt would be ~/.myfile.txt.swp)." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-diff - Show changes between commits, commit and working tree, etc cumulative" }, { "role": "assistant", "content": "Count changes in a child directory for the parent directory as well.\nNote that when using cumulative , the sum of the percentages\nreported may exceed 100%. The default (non-cumulative) behavior can\nbe specified with the noncumulative parameter." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How to fix Invocation failed Unexpected Response from Server: Unauthorized in Android studio\nI have one project on Gitlab and I worked with it for the last few days!\nNow i want pull project on my home PC but show me below error : \nInvocation failed Unexpected Response from Server: Unauthorized\n java.lang.RuntimeException: Invocation failed Unexpected Response from Server: Unauthorized\n at org.jetbrains.git4idea.nativessh.GitNativeSshAskPassXmlRpcClient.handleInput(GitNativeSshAskPassXmlRpcClient.java:34)\n at org.jetbrains.git4idea.nativessh.GitNativeSshAskPassApp.main(GitNativeSshAskPassApp.java:30)\n Caused by: java.io.IOException: Unexpected Response from Server: Unauthorized\n at org.apache.xmlrpc.LiteXmlRpcTransport.sendRequest(LiteXmlRpcTransport.java:231)\n at org.apache.xmlrpc.LiteXmlRpcTransport.sendXmlRpc(LiteXmlRpcTransport.java:90)\n at org.apache.xmlrpc.XmlRpcClientWorker.execute(XmlRpcClientWorker.java:72)\n at org.apache.xmlrpc.XmlRpcClient.execute(XmlRpcClient.java:194)\n at org.apache.xmlrpc.XmlRpcClient.execute(XmlRpcClient.java:185)\n at org.apache.xmlrpc.XmlRpcClient.execute(XmlRpcClient.java:178)\n\nMy android studio version is 3.4 !" }, { "role": "assistant", "content": "Enabling credentials helper worked for me, using Android Studio 3.6.2 on Windows 10\nAndroidStudio -> File -> Settings -> Git -> Use credential helper" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "gitworkflows - An overview of recommended workflows with Git" }, { "role": "assistant", "content": "DESCRIPTION This document attempts to write down and motivate some of the workflow\nelements used for git.git itself. Many ideas apply in general,\nthough the full workflow is rarely required for smaller projects with\nfewer people involved. We formulate a set of rules for quick reference, while the prose\ntries to motivate each of them. Do not always take them literally;\nyou should value good reasons for your actions higher than manpages\nsuch as this one." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-shortlog - Summarize git log output --show-pulls" }, { "role": "assistant", "content": "In addition to the commits shown in the default history, show\neach merge commit that is not TREESAME to its first parent but\nis TREESAME to a later parent. When a merge commit is included by --show-pulls , the merge is\ntreated as if it \"pulled\" the change from another branch. When using --show-pulls on this example (and no other options) the resulting\ngraph is: I---X---R---N Here, the merge commits R and N are included because they pulled\nthe commits X and R into the base branch, respectively. These\nmerges are the reason the commits A and B do not appear in the\ndefault history. When --show-pulls is paired with --simplify-merges , the\ngraph includes all of the necessary information: .-A---M--. N\n\t / / \\ /\n\tI B R\n\t \\ / /\n\t \\ / /\n\t `---X--' Notice that since M is reachable from R , the edge from N to M was simplified away. However, N still appears in the history as an\nimportant commit because it \"pulled\" the change R into the main\nbranch." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Amend the second to last commit\nIf you found a bug in your last commit, you can simply recommit the last commit with\ngit commit --amend\n\nBut if you already committed another commit, how do you resubmit the commit before that one?\n\nNote: I assume, you are aware, that you should only use --amend if you are sure no other developer already used your commit upstream" }, { "role": "assistant", "content": "commit your fixup with \ngit commit -a -m \"fix commit (this one will be shifted up one line)\"\n(the commit message is not important, it will be obsolete once you are finished)\nNow the magic:\nrebase the HEAD to the second last commit but edit the commit message before in that way, that you swap the last and the last but one line in the message editor:\ngit rebase -i HEAD~3\nThe editor will show the last 3 comits like this: \n pick 2a06f16 this was the last commit\n pick 0dbc5ce the last-but-one commit\n pick 2e30418 fix commit (this one will be shifted up one line)\n\n # Rebase 011f3d0..2e30418 onto 011f3d0\n # …\n\nswap the last two lines so the commit message will look for example like this: \n pick 2a06f16 this was the last commit\n fixup 2e30418 fix commit (this one will be shifted up one line)\n pick 0dbc5ce the last-but-one commit\n\n # Rebase 011f3d0..2e30418 onto 011f3d0\n # …\n\nCheck your log with\ngit log HEAD~3\npush the corrected commit-line with + to force a new push to the already existing branch with\ngit push origin +branchname" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How to cherry-pick from stash in git?\nI am wondering if cherry-picking from stash is possible.\ngit stash save \"test cherry-pick from stash\"\n\ngit cherry-pick stash@{0} # --> Is this possible?\n\nI am getting the following error when I tried above command:\n~/Documents$ git cherry-pick stash@{0}\nerror: Commit 4590085c1a0d90de897633990f00a14b04405350 is a merge but no -m option was given.\nfatal: cherry-pick failed" }, { "role": "assistant", "content": "The problem is that a stash consists of two or three commits. When stashing, the modified working tree is stored in one commit, the index in one commit, and (if using the --include-untracked flag) any untracked files in a third commit.\nYou can see this if you use gitk --all and do a stash.\n\nstash@{0} points to the commit that contains the working tree.\nYou can however cherry-pick from that commit if you do\ngit cherry-pick \"stash@{0}\" -m 1\n\nThe reason that cherry-pick thinks that the stash is a merge, and thus needs the -m 1 parameter is that the stash commit has multpile parents, as you can see in the graph.\nI am not sure exactly what you want to achieve by cherry-picking. A possible alternative is to create a branch from the stash. Commit changes there and merge them to your current branch.\ngit stash branch stashchanges\ngit commit -a -m \"changes that were stashed\"\ngit checkout master\ngit merge stashchanges" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Nested git repositories without submodules?\nIt seems a git repo inside a parent repo isn't included in a commit on the parent unless it's setup as a submodule. Is it possible to override this behaviour and treat the nested git repo as any other directory? I don't want to rely on external dependencies through submodules but want to use git to manage these dependencies within the project." }, { "role": "assistant", "content": "1/ You could override that through:\n\neither a git config setting: set the environment variable $GIT_DIR\nyou define your .git directory of the nested Git working tree as an external .git (external to both the nested repo and the main repo) \nor by setting your nested repo 'N' outside the main repo, but checkout that repo 'N' inside the main repo: \n\ncore.worktree\nSet the path to the root of the work tree. This can be overridden by the GIT_WORK_TREE environment variable and the --work-tree command line option\nIn both case, the idea is to have a nested worktree without any .git subdirectory in it.\n2/ With submodules, the nested git repo is not really included in the parent repo.\nA special entry is made in the parent tree to record the external Git SHA1.\nnew file mode 160000\nindex 0000000..4c4c5a2\n\nSee also \"nature of Git submodules\" (third part of the answer)\n\nNine years later, this discussion is quite clear:\n\n\nI don't want to use submodules or crutches\n such as renaming all .git/ in subdirectories.\n I just want that Git treats my .git/ subdirs as plain dirs with any other names.\n\n\nBrian m. Carlson (bk2204) answers:\n\nThis is not possible.\n You can't add a non-bare repository as a part of a parent repository without using submodules.\n Git uses the .git directory to find the working tree and for safety reasons doesn't allow files or directories named that to be checked in.\n Allowing users to check in .git directories would allow configuration and hooks to be stored as part of the repository, which would allow the execution of arbitrary code if someone cloned it and then changed into the\n subrepository." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git is not respecting gitignore instruction to ignore .env files\nI have a project. In the root directory are these 4 files:\n\n.env .env.example .env.local .env.staging\n\nI have a .gitignore file, and I'm listing these 4 files in the .gitignore, one after another, like this\n.env\n.env.example\n.env.local\n.env.staging\n\nMy git repository does not contain .env or .env.example, but it DOES contain .env.local and .env.staging.\nI've tried everything I can think of, but it keeps syncing these 2 files with git.\nAny ideas what could be causing this?" }, { "role": "assistant", "content": "Use git rm:\nIf you have already added the files to be tracked, you need to remove them from tracking:\ngit rm env.local --cached\ngit rm env.staging --cached\ngit commit -m \"Stopped tracking env.local, and env.staging\"\n\nNow you should be able to clone your branch without those files being tracked.\nNote: Keep in mind that the contents of those files are in your history, and if they did contain sensitive data, then you need to completely remove that from history before putting it out there." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-branch - List, create, or delete branches" }, { "role": "assistant", "content": "NOTES If you are creating a branch that you want to switch to immediately,\nit is easier to use the \"git switch\" command with its -c option to\ndo the same thing with a single command. The options --contains , --no-contains , --merged and --no-merged serve four related but different purposes: --contains <commit> is used to find all branches which will need\nspecial attention if <commit> were to be rebased or amended, since those\nbranches contain the specified <commit>. --no-contains <commit> is the inverse of that, i.e. branches that don’t\ncontain the specified <commit>. --merged is used to find all branches which can be safely deleted,\nsince those branches are fully contained by HEAD. --no-merged is used to find branches which are candidates for merging\ninto HEAD, since those branches are not fully contained by HEAD. When combining multiple --contains and --no-contains filters, only\nreferences that contain at least one of the --contains commits and\ncontain none of the --no-contains commits are shown. When combining multiple --merged and --no-merged filters, only\nreferences that are reachable from at least one of the --merged commits and from none of the --no-merged commits are shown." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-log - Show commit logs --full-history" }, { "role": "assistant", "content": "Same as the default mode, but does not prune some history." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Git 'fatal: Unable to write new index file'\nI've seen many of the other threads about this and they don't help.\nI have a very simple repo - two JavaScript files. I have 100+ GB on Macbook. When I try to move the files into a subdirectory and stage locally the changes I get ...\n\nfatal: Unable to write new index file\n\nThis happens whether I do all actions in terminal or if I use a GUI like SourceTree. Additionally, one of the files becomes locked and I cannot delete the working directory until I log off and back in.\nWhy is this happening? Is the lock preventing something from staging? If so, what/how do I unlock the problem file on OS X?? The remote repo is Google Code, if that makes a difference, though I am not pushing to the remote yet. Everything is local." }, { "role": "assistant", "content": "In my case, the disk ran out of space, so I had to delete files from the hard drive to make space." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-submodule - Initialize, update or inspect submodules --[no-]single-branch" }, { "role": "assistant", "content": "This option is only valid for the update command.\nClone only one branch during update: HEAD or one specified by --branch." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-log - Show commit logs -D --irreversible-delete" }, { "role": "assistant", "content": "Omit the preimage for deletes, i.e. print only the header but not\nthe diff between the preimage and /dev/null . The resulting patch\nis not meant to be applied with patch or git apply ; this is\nsolely for people who want to just concentrate on reviewing the\ntext after the change. In addition, the output obviously lacks\nenough information to apply such a patch in reverse, even manually,\nhence the name of the option. When used together with -B , omit also the preimage in the deletion part\nof a delete/create pair." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Automatically Deploy From GitHub To Server On Push\nWe have a VPS on Linode, and code hosted on GitHub. How do we setup so when we push to GitHub, it also pushes automatically to our Linode server. We are using PHP on the Linode server." }, { "role": "assistant", "content": "You probably want to use GitHub's post-receive hooks.\nIn summary, GitHub will POST to a supplied URL when someone pushes to the repo. Just write a short PHP script to run on your linode VPS and pull from GitHub when it receives said POST." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Storing secrets and credentials securely in GitLab\n\nI am wondering if it's possible to store credentials like passwords, tokens and keys safely in my GitLab project.\nCurrently there are a bunch of Java files with some passwords stored in it for testing purposes. However, I don't want to push this information on my repo due to security reasons. I tried using environment variables in the project, but they only seem to work for the .gitlab-ci.yml file.\nMy question is does anyone use a vault like Hashicorps or Blackbox to encrypt sensitive information?\nThanks" }, { "role": "assistant", "content": "If you are not using environment variables in GitLab, then you are asking if it is possible to store secrets in GitLab. I have not done this myself, but I found this post about it:\nhttps://embeddedartistry.com/blog/2018/03/15/safely-storing-secrets-in-git/\nThe author suggests three ways of storing secrets in git:\n\nBlackbox\ngit-secret\ngit-crypt\n\nThe author was using BlackBox, but was going to migrate to git-crypt. From a quick look at it, git-crypt looks like something that I could use myself." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Git: error: RPC failed; result=22, HTTP code = 411\n\nSymptoms:\nGit suddenly refused to push a repository (to github in my case):\n$ git push\nCounting objects: 9292, done.\nDelta compression using up to 8 threads.\nCompressing objects: 100% (2136/2136), done.\nerror: RPC failed; result=22, HTTP code = 411\nfatal: The remote end hung up unexpectedly\nWriting objects: 100% (8222/8222), 1.27 MiB \| 837 KiB/s, done.\nTotal 8222 (delta 6060), reused 8181 (delta 6033)\nfatal: The remote end hung up unexpectedly\nEverything up-to-date" }, { "role": "assistant", "content": "Here is what helped, the following command increases git buffer to 500mb:\ngit config http.postBuffer 524288000" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-rev-parse - Pick out and massage parameters --revs-only" }, { "role": "assistant", "content": "Do not output flags and parameters not meant for git rev-list command." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Can \"git pull\" automatically stash and pop pending changes?\nI know how to solve this:\nuser@host$ git pull\nUpdating 9386059..6e3ffde\nerror: Your local changes to the following files would be overwritten by merge:\n foo.bar\nPlease, commit your changes or stash them before you can merge.\nAborting\n\nBut isn't there a way to let git pull do the stash and pop dance for me?\nIf this command has a different name, it's ok.\nCreating a shell alias for git stash; git pull; git stash pop is a solution, but I search for a better solution." }, { "role": "assistant", "content": "For Git 2.6+ (released 28 Sept 2015)\nThe only git config setting which would be of interest is:\n\nrebase.autostash\n\n(with Git 2.27, Q2 2020, you now also have merge.autostash, see below)\n\nWhen set to true, automatically create a temporary stash before the operation begins, and apply it after the operation ends.\nThis means that you can run rebase on a dirty worktree.\nHowever, use with care: the final stash application after a successful rebase might result in non-trivial conflicts. Defaults to false.\n\nCombine that with:\n\npull.rebase\n\n\nWhen true, rebase branches on top of the fetched branch, instead of merging the default branch from the default remote when \"git pull\" is run.\n\nIn a given repository:\ngit config pull.rebase true\ngit config rebase.autoStash true\n\nThat would be enough for a simple git pull to work even in a dirty tree.\nNo alias needed in that case.\n\nSee commit 53c76dc (04 Jul 2015) by Kevin Daudt (Ikke).\n(Merged by Junio C Hamano -- gitster -- in commit e69b408, 17 Aug 2015)\n\npull: allow dirty tree when rebase.autostash enabled\n\n\nrebase learned to stash changes when it encounters a dirty work tree,\nbut git pull --rebase does not.\nOnly verify if the working tree is dirty when rebase.autostash is not\nenabled.\n\n\nNote: if you want to pull without autostash (even though rebase.autoStash true is set), you have since git 2.9 (June 2016):\n pull --rebase --no-autostash\n\nSee commit 450dd1d, commit 1662297, commit 44a59ff, commit 5c82bcd, commit 6ddc97c, commit eff960b, commit efa195d (02 Apr 2016), and commit f66398e, commit c48d73b (21 Mar 2016) by Mehul Jain (mehul2029).\n(Merged by Junio C Hamano -- gitster -- in commit 7c137bb, 13 Apr 2016)\nCommit f66398e in particular includes:\n\npull --rebase: add --[no-]autostash flag\n\n\nIf rebase.autoStash configuration variable is set, there is no way to\noverride it for \"git pull --rebase\" from the command line.\nTeach \"git pull --rebase\" the --[no-]autostash command line flag which\noverrides the current value of rebase.autoStash, if set. As \"git rebase\"\nunderstands the --[no-]autostash option, it's just a matter of passing\nthe option to underlying \"git rebase\" when \"git pull --rebase\" is called.\n\n\nWarning: before Git 2.14 (Q3 2017), \"git pull --rebase --autostash\" didn't auto-stash when the local history fast-forwards to the upstream.\nSee commit f15e7cf (01 Jun 2017) by Tyler Brazier (tylerbrazier).\n(Merged by Junio C Hamano -- gitster -- in commit 35898ea, 05 Jun 2017)\n\npull: ff --rebase --autostash works in dirty repo\n\n\nWhen git pull --rebase --autostash in a dirty repository resulted in a\nfast-forward, nothing was being autostashed and the pull failed.\nThis was due to a shortcut to avoid running rebase when we can fast-forward,\nbut autostash is ignored on that codepath.\n\n\nUpdate: Mariusz Pawelski asks in the comments an interesting question:\n\nSo everybody is writing about autostash when you do rebase (or pull --rebase).\n\n\nBut no one is taking about autostashing when you do normal pull with merges.\nSo there is no automatic switch for that? Or I am missing something? I prefer doing git pull --rebase but OP asked about \"standard\" git pull\n\nAnswer:\nThe original thread discussing this autostash feature, it was implemented originally both for git pull (merge) and git pull --rebase.\nBut... Junio C Hamano (Git maintainer) noted that:\n\nIf the pull-merge were something that would induce the \"annoyance\"\nthat triggered this topic, by definition, the local change overlaps\nwith the merge, and this internal \"stash pop\" will touch the paths\nthe merge touched and it is likely not result in \"Dropped\" but leave\nfurther conflicts to be resolved.\nI suspect that pull.autostash configuration is not a good addition because it encourages a bad, pain-inducing workflow.\nIn simple cases it may not hurt, but when local changes are complex, it would actively hurt than not having it, and the configuration robs the incentive to choose.\nThe equation is somewhat different for \"pull-rebase\", as \"rebase\"\ninsists you to start from a clean working tree, so \"download and\nthen stop\" annoyance feels bigger. I have a suspicion that\nloosening that may be a more productive fix to the real problem.\n\nSo, regarding a classic pull-merge, it is better to:\n\nencourage the user to think about the nature of WIP he has in the working tree before running \"git pull\".\nIs it a too complex beast that may interfere with what others are doing, or\nis it a trivial change that he can stash away and pop it back?\nIf the former, he will be far better off doing \"checkout -b\", keep\nworking until the local change gets into somewhat a better shape and\n\"commit\", before pulling into the original branch.\nIf the latter, he is better off doing:\n\n\n\n\"git pull\",\nafter finding it conflicts, run\n\ngit stash,\ngit merge FETCH_HEAD and\ngit stash pop\n\n\n\n\n\nThat being said, with Git 2.27 (Q2 2020), \"git pull\" learned to warn when no pull.rebase configuration exists, and neither --[no-]rebase nor --ff-only is given (which would result a merge).\nSee commit d18c950 (10 Mar 2020) by Alex Henrie (alexhenrie).\n(Merged by Junio C Hamano -- gitster -- in commit 1c56d6f, 27 Mar 2020)\n\npull: warn if the user didn't say whether to rebase or to merge\nSigned-off-by: Alex Henrie\n\n\nOften novice Git users forget to say \"pull --rebase\" and end up with an unnecessary merge from upstream.\nWhat they usually want is either \"pull --rebase\" in the simpler cases, or \"pull --ff-only\" to update the copy of main integration branches, and rebase their work separately.\nThe pull.rebase configuration variable exists to help them in the simpler cases, but there is no mechanism to make these users aware of it.\nIssue a warning message when no --[no-]rebase option from the command line and no pull.rebase configuration variable is given.\nThis will inconvenience those who never want to \"pull --rebase\", who haven't had to do anything special, but the cost of the inconvenience is paid only once per user, which should be a reasonable cost to help a number of new users.\n\n\nWith Git 2.27 (Q2 2020), \"git merge\" learns the \"--autostash\" option, and the new merge.autostash setting.\nSee commit d9f15d3, commit f8a1785, commit a03b555, commit 804fe31, commit 12b6e13, commit 0dd562e, commit 0816f1d, commit 9bb3dea, commit 4d4bc15, commit b309a97, commit f213f06, commit 86ed00a, commit facca7f, commit be1bb60, commit efcf6cf, commit c20de8b, commit bfa50c2, commit 3442c3d, commit 5b2f6d9 (07 Apr 2020), commit 65c425a (04 Apr 2020), and commit fd6852c, commit 805d9ea (21 Mar 2020) by Denton Liu (Denton-L).\n(Merged by Junio C Hamano -- gitster -- in commit bf10200, 29 Apr 2020)\n\npull: pass --autostash to merge\nSigned-off-by: Denton Liu\n\n\nBefore, --autostash only worked with git pull --rebase.\nHowever, in the last patch, merge learned --autostash as well so there's no reason why we should have this restriction anymore.\nTeach pull to pass --autostash to merge, just like it did for rebase.\n\nAnd:\n\nrebase: use apply_autostash() from sequencer.c\nSigned-off-by: Denton Liu\n\n\nThe apply_autostash() function in builtin/rebase.c is similar enough to the apply_autostash() function in sequencer.c that they are almost interchangeable, except for the type of arg they accept. Make the sequencer.c version extern and use it in rebase.\nThe rebase version was introduced in 6defce2b02 (\"builtin rebase: support --autostash option\", 2018-09-04, Git v2.20.0-rc0 -- merge listed in batch #8) as part of the shell to C conversion.\nIt opted to duplicate the function because, at the time, there was another in-progress project converting interactive rebase from shell to C as well and they did not want to clash with them by refactoring sequencer.c version of apply_autostash().\nSince both efforts are long done, we can freely combine them together now.\n\n\nWith Git 2.30 (Q1 2021), the UI is improved:\nSee commit e01ae2a (19 Nov 2020) by Johannes Schindelin (dscho).\n(Merged by Junio C Hamano -- gitster -- in commit 290c940, 30 Nov 2020)\n\npull: colorize the hint about setting pull.rebase\nPointed-out-by: Ævar Arnfjörð Bjarmason\nSigned-off-by: Johannes Schindelin\n\n\nIn d18c950a69f (\"pull: warn if the user didn't say whether to rebase or to merge\", 2020-03-09, Git v2.27.0-rc0 -- merge listed in batch #2), a new hint was introduced to encourage users to make a conscious decision about whether they want their pull to merge or to rebase by configuring the pull.rebase setting.\nThis warning was clearly intended to advise users, but as pointed out in this thread, it uses warning() instead of advise().\nOne consequence is that the advice is not colorized in the same manner as other, similar messages.\nSo let's use advise() instead.\n\n\nWith Git 2.33 (Q3 2021), git pull --rebase is simplified:\nSee commit a7d18a1, commit a751e02, commit 3400622 (17 Jun 2021) by Felipe Contreras (felipec).\n(Merged by Junio C Hamano -- gitster -- in commit 221ec24, 08 Jul 2021)\n\npull: cleanup autostash check\nSigned-off-by: Felipe Contreras\n\n\nCurrently \"git pull --rebase\"(man) takes a shortcut in the case a fast-forward merge is possible; run_merge() is called with --ff-only.\nHowever, \"git merge\"(man) did ont have an --autostash option, so, when \"git pull --rebase --autostash``\"(man) was called and the fast-forward merge shortcut was taken, then the pull failed.\nThis was fixed in commit f15e7cf (\"pull: ff --rebase --autostash works in dirty repo\", 2017-06-01, Git v2.14.0-rc0 -- merge listed in batch #7) by simply skipping the fast-forward merge shortcut.\nLater on \"git merge\" learned the --autostash option [a03b555 (\"merge: teach --autostash option\", 2020-04-07, Git v2.27.0-rc0 -- merge listed in batch #5)], and so did \"git pull\"(man) [d9f15d3 (\"pull: pass --autostash to merge\", 2020-04-07, Git v2.27.0-rc0 -- merge listed in batch #5)].\nTherefore it's not necessary to skip the fast-forward merge shortcut anymore when called with --rebase --autostash.\nLet's always take the fast-forward merge shortcut by essentially reverting f15e7cf.\n\n\nThe auto-stashed local changes created by \"git merge --autostash\"(man) was mixed into a conflicted state left in the working tree, which has been corrected with Git 2.38 (Q3 2022).\nSee commit d3a9295 (23 Aug 2022) by Elijah Newren (newren).\n(Merged by Junio C Hamano -- gitster -- in commit 3a47790, 01 Sep 2022)\n\nmerge: only apply autostash when appropriate\nSigned-off-by: Elijah Newren\n\n\nIf a merge failed and we are leaving conflicts in the working directory for the user to resolve, we should not attempt to apply any autostash.\nFurther, if we fail to apply the autostash (because either the merge failed, or the user requested --no-commit), then we should instruct the user how to apply it later.\nAdd a testcase verifying we have corrected this behavior.\n\nThe new instructions:\n\nWhen finished, apply stashed changes with git stash pop." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How can I download a single raw file from a private github repo using the command line?\n\nOn the CI server, I want to fetch a config file that we maintain on Github so it can be shared between many jobs. I'm trying to get this file via curl, but these approaches both fail (I get a 404):\n# As advised by the oAuth docs\ncurl -H 'Authorization: token the_token' -L -o setup.sh https://raw.github.com/org/repo/file\n\n# The url of the raw file after clicking to view it\ncurl -L https://raw.github.com/org/repo/file?login=username&token=the_token" }, { "role": "assistant", "content": "The previous answers don't work (or don't work anymore).\nYou can use the V3 API to get a raw file like this (you'll need an OAuth token):\ncurl -H 'Authorization: token INSERTACCESSTOKENHERE' \\\n -H 'Accept: application/vnd.github.v3.raw' \\\n -O \\\n -L https://api.github.com/repos/owner/repo/contents/path\n\nAll of this has to go on one line. The -O option saves the file in the current directory. You can use -o filename to specify a different filename.\nTo get the OAuth token follow the instructions here:\n\nhttps://help.github.com/articles/creating-an-access-token-for-command-line-use\n\nI've written this up as a gist as well:\n\nhttps://gist.github.com/madrobby/9476733\n\nEDIT: API references for the solution are as follows:\n\nhttps://developer.github.com/v3/#authentication\nhttps://developer.github.com/v3/media/#request-specific-version\nhttps://developer.github.com/v3/repos/contents/#get-contents" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-config - Get and set repository or global options diff.wsErrorHighlight" }, { "role": "assistant", "content": "Highlight whitespace errors in the context , old or new lines of the diff. Multiple values are separated by comma, none resets previous values, default reset the list to new and all is a shorthand for old,new,context . The\nwhitespace errors are colored with color.diff.whitespace .\nThe command line option --ws-error-highlight=<kind> overrides this setting." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How to get the short sha for the github workflow?\nI am creating a workflow in GitHub which creates and uses a docker image. Therefore I have started my workflow file with a global environment variable for this docker image which is visible for all the jobs in my workflow:\nname: continuous integration\non:\n push:\n branches:\n - '**'\n\nenv:\n IMAGE: docker.pkg.github.com/${{ github.repository }}/jactor-persistence:${{ github.sha }}\n\nI want to replace ${{ github.sha }} with the short sha of the head commit, the same as the result of the following command git rev-parse --short HEAD\nIs this possible?" }, { "role": "assistant", "content": "As VonC mentioned, you can just compute the string yourself in a previous step.\n - name: Set outputs\n id: vars\n run: echo \"sha_short=$(git rev-parse --short HEAD)\" >> $GITHUB_OUTPUT\n - name: Check outputs\n run: echo ${{ steps.vars.outputs.sha_short }}" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-log - Show commit logs separate" }, { "role": "assistant", "content": "Show full diff with respect to each of parents.\nSeparate log entry and diff is generated for each parent." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git - the stupid content tracker git-mktag" }, { "role": "assistant", "content": "Creates a tag object with extra validation" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-symbolic-ref - Read, modify and delete symbolic refs" }, { "role": "assistant", "content": "NOTES In the past, .git/HEAD was a symbolic link pointing at refs/heads/master . When we wanted to switch to another branch,\nwe did ln -sf refs/heads/newbranch .git/HEAD , and when we wanted\nto find out which branch we are on, we did readlink .git/HEAD .\nBut symbolic links are not entirely portable, so they are now\ndeprecated and symbolic refs (as described above) are used by\ndefault. git symbolic-ref will exit with status 0 if the contents of the\nsymbolic ref were printed correctly, with status 1 if the requested\nname is not a symbolic ref, or 128 if another error occurs." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git - the stupid content tracker --namespace=<path>" }, { "role": "assistant", "content": "Set the Git namespace. See gitnamespaces for more\ndetails. Equivalent to setting the GIT_NAMESPACE environment\nvariable." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Git 'fatal: No such ref: HEAD'\nA weird thing happend to my git repository. When I try to commit something in tortoisegit window I receive all files from project. I cannot revert them, when I pull from server I receive fatal: No such ref: HEAD and fatal: Cannot lock the ref 'HEAD'. All my local branches are missing. Is there any way to resolve the problem?\nThis is not first commit or something. This thing happend suddenly.\nEDIT:\ngit branch -a says: Failed to resolve HEAD as a valid ref\ngit status prints all project files marked as new file.\nI changed repository folder name for a while, and when I changed it back things were not correct." }, { "role": "assistant", "content": "You've lost your HEAD so you'll need to recreate it. The simplest thing to do is this.\necho ref: refs/heads/master >.git/HEAD\n\nNow you should be able to run other git commands and see where you're at.\n(Although, in theory, you could attempt to do git symbolic-ref HEAD refs/heads/master newer git versions don't recognize a .git as a git repository unless it already contains a HEAD so this won't work to create a new one.)" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-clone - Clone a repository into a new directory --separate-git-dir= <git-dir>" }, { "role": "assistant", "content": "Instead of placing the cloned repository where it is supposed\nto be, place the cloned repository at the specified directory,\nthen make a filesystem-agnostic Git symbolic link to there.\nThe result is Git repository can be separated from working\ntree." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-diff - Show changes between commits, commit and working tree, etc --histogram" }, { "role": "assistant", "content": "Generate a diff using the \"histogram diff\" algorithm." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Fatal: Not a gitflow-enabled repo yet. Please run 'git flow init' first\n\nI cloned a project and ran git checkout -b develop. When I run git flow feature start feature_name it gives me the following error:\n\nFatal: Not a gitflow-enabled repo yet. Please run 'git flow init' first.\n\ncan any one help me?" }, { "role": "assistant", "content": "I got it working by doing the steps mentioned by jpfl @ answers.atlassian.com:\n\nAlthough this is an old post, just wanted to add to this since I've\n gotten stuck on this same error. Was able to resolve by doing the\n following:\n\nOpen the .git\\config file OR Repository -> Repository Settings -> Remotes -> Edit Config File (Sourcetree 2.7.6)\nRemove all the [gitflow * entries and save\n the file \nClose and re-open SourceTree \nIn the main menu, go to\n Repository > Git Flow > Initialise Repository (should be enabled\n now)" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-pull - Fetch from and integrate with another repository or a local branch --refmap=<refspec>" }, { "role": "assistant", "content": "When fetching refs listed on the command line, use the\nspecified refspec (can be given more than once) to map the\nrefs to remote-tracking branches, instead of the values of remote.*.fetch configuration variables for the remote\nrepository. Providing an empty <refspec> to the --refmap option causes Git to ignore the configured\nrefspecs and rely entirely on the refspecs supplied as\ncommand-line arguments. See section on \"Configured Remote-tracking\nBranches\" for details." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How to create a new branch on both local and remote? GIT [duplicate]\nThis question already has answers here:\n \n \n\n\n\n\nHow do I create a remote Git branch?\n\n (26 answers)\n \n\nClosed 8 years ago.\n\n\n\nI create a new branch like this:\n\ngit branch dev-itt-9\n\nHowever, it only creates a new branch on local\n\ngit branch -a\n\n* dev-itt-9\n master\n testing\n\n remotes/origin/HEAD -> origin/master\n remotes/origin/development\n remotes/origin/master\n remotes/origin/testing\n\nWhat is the proper way to create a new branch on both local and remote?\nI am quite new to git. Sorry if my question is stupid." }, { "role": "assistant", "content": "First, you create your branch locally:\ngit checkout -b <branch-name>\n\nThe remote branch is automatically created when you push it to the remote server. So when you feel ready for it, you can just do:\ngit push <remote-name> <branch-name>\n\nWhere <remote-name> is typically origin, the name which git gives to the remote you cloned from. Your colleagues would then just pull that branch, and it's automatically created locally.\n\nCredit: this answer is a copy of https://stackoverflow.com/a/1519032" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Filter git log to show only my changes\nHow can I filter the git log to show only my changes (excluding the changes committed by other developers)?" }, { "role": "assistant", "content": "You can filter the log by the author for example, so you can filter by your name :\ngit log --author=\"YourName\"\n\nor by committer : \n git log --committer=\"YourName\"" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "gitlab-runner locally - No such command sh\n\nI have gitlab-runner installed locally. \nkm@Karls-MBP ~ $ gitlab-runner --version\nVersion: 10.4.0\nGit revision: 857480b6\nGit branch: 10-4-stable\nGO version: go1.8.5\nBuilt: Mon, 22 Jan 2018 09:47:12 +0000\nOS/Arch: darwin/amd64\n\nDocker:\nkm@Karls-MBP ~ $ docker --version\nDocker version 17.12.0-ce, build c97c6d6\n\n.gitlab-ci.yml:\nimage: docker/compose:1.19.0\n\nbefore_script:\n - echo wtf\n\ntest:\n script:\n - echo test\n\nResults:\nkm@Karls-MBP ~ $ sudo gitlab-runner exec docker --docker-privileged test\nWARNING: Since GitLab Runner 10.0 this command is marked as DEPRECATED and will be removed in one of upcoming releases \nWARNING: You most probably have uncommitted changes. \nWARNING: These changes will not be tested. \nRunning with gitlab-runner 10.4.0 (857480b6)\n on ()\nUsing Docker executor with image docker/compose:1.19.0 ...\nUsing docker image sha256:be4b46f2adbc8534c7f6738279ebedd6106969695f5e596079e89e815d375d9c for predefined container...\nPulling docker image docker/compose:1.19.0 ...\nUsing docker image docker/compose:1.19.0 ID=sha256:e06b58ce9de2ea3f11634e022ec814984601ea3a5180440c2c28d9217b713b30 for build container...\nRunning on runner--project-0-concurrent-0 via x.x.x...\nCloning repository...\nCloning into '/builds/project-0'...\ndone.\nChecking out b5a262c9 as km/ref...\nSkipping Git submodules setup\nNo such command: sh\n\nCommands:\n build Build or rebuild services\n bundle Generate a Docker bundle from the Compose file\n config Validate and view the Compose file\n create Create services\n down Stop and remove containers, networks, images, and volumes\n events Receive real time events from containers\n exec Execute a command in a running container\n help Get help on a command\n images List images\n kill Kill containers\n logs View output from containers\n pause Pause services\n port Print the public port for a port binding\n ps List containers\n pull Pull service images\n push Push service images\n restart Restart services\n rm Remove stopped containers\n run Run a one-off command\n scale Set number of containers for a service\n start Start services\n stop Stop services\n top Display the running processes\n unpause Unpause services\n up Create and start containers\n version Show the Docker-Compose version information\n\nDon't really know what the issue is." }, { "role": "assistant", "content": "It seems that the docker/compose image is configured with docker-compose as an entrypoint.\nYou can override the default entrypoint of the docker/compose image in your .gitlab-ci.yml file :\nimage: \n name: docker/compose:1.19.0\n entrypoint: [\"\"]\n\nbefore_script:\n - echo wtf\n\ntest:\n script:\n - echo test" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How to use git (git config --global)?\nThe Pragmatic Guide to GIT has the following \"Git uses both to calculate the commit ID—a SHA-111 hash—that identifies each commit.\" in page 21.\nAnd in page 22, I can use the following command to 'Configure Git to know who you are'.\n\ngit config --global smcho \"Your Name\"\n\nWhen I ran it, I got the following error message. \n\nerror: key does not contain a section: smcho\n\nWhat's wrong with this? I guess it has something to do with SHA-111 hash, but I don't know how to get it to be used with git. \nADDED\nI thought user.name is to be replaced my name, not a section/parameter structured name. After changing that it works OK. \n\ngit config --global user.name \"Your Name\"" }, { "role": "assistant", "content": "Not sure where \"smcho\" comes from, but the setting to set your name is user.name:\ngit config --global user.name \"Your Name\"\n\nYou can set your e-mail address too:\ngit config --global user.email \"[email protected]\"\n\nI guess the reason it complains about the lack of a section is that the name of the parameter to set probably needs to be in two parts: section.parameter_name (You can see the sections names within [] if you look in the configuration file, for example in .git/config).\n(None of this is specific to OSX as far as I'm aware.)" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-reset - Reset current HEAD to the specified state --hard" }, { "role": "assistant", "content": "Resets the index and working tree. Any changes to tracked files in the\nworking tree since <commit> are discarded. Any untracked files or\ndirectories in the way of writing any tracked files are simply deleted." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-apply - Apply a patch to files and/or to the index -v --verbose" }, { "role": "assistant", "content": "Report progress to stderr. By default, only a message about the\ncurrent patch being applied will be printed. This option will cause\nadditional information to be reported." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Git push error: \"origin does not appear to be a git repository\"\nI am following the instructions given here to create a Git repository. All went well until the last line: \n$ git push -u origin master \n\n\nfatal: 'origin' does not appear to be a git repository\n fatal: The remote end hung up unexpectedly\n\nI'm using git version 1.7.11.3 on OS X 10.6.8\n$ git remote -v \n\nreturns nothing\nConfig file for the repository: \n[core]\nrepositoryformatversion = 0 \nfilemode = true \nbare = false\nlogallrefupdates = true \nignorecase = true \n\nI've had to open sudoers file using sudo visudo command and add the following to it (under # User privilege specification): \ngit ALL=(ALL) ALL. \n\nNow if I do: \n$ git remote add origin /Volumes/500GB/git-repository/myproject.git \n\nit comes back with no error, but I don't see any code in the repository\n(it has the aforementioned directories like branches, hooks, ...) \nIf I do:\n$ git push -u origin master \nfatal: 'origin' does not appear to be a git repository\nfatal: The remote end hung up unexpectedly\n\n$ git remote -v \norigin /Volumes/500GB/git-repository/myproject.git (fetch) \norigin /Volumes/500GB/git-repository/myproject.git (push)" }, { "role": "assistant", "content": "As it has already been mentioned in che's answer about adding the remote part, which I believe you are still missing.\nRegarding your edit for adding remote on your local USB drive. First of all you must have a 'bare repository' if you want your repository to be a shared repository i.e. to be able to push/pull/fetch/merge etc..\nTo create a bare/shared repository, go to your desired location. In your case:\n$ cd /Volumes/500gb/ \n$ git init --bare myproject.git\n\nSee here for more info on creating bare repository\nOnce you have a bare repository set up in your desired location you can now add it to your working copy as a remote.\n$ git remote add origin /Volumes/500gb/myproject.git\n\nAnd now you can push your changes to your repository\n$ git push origin master" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Git: Remove committed file after push\nIs there a possibility to revert a committed file in Git? I've pushed a commit to GitHub and then I realized that there's a file which I didn't want to be pushed (I haven't finished the changes)." }, { "role": "assistant", "content": "update: added safer method\npreferred method:\n\ncheck out the previous (unchanged) state of your file; notice the double dash \ngit checkout HEAD^ -- /path/to/file\n\ncommit it:\ngit commit -am \"revert changes on this file, not finished with it yet\"\n\npush it, no force needed:\ngit push\n\nget back to your unfinished work, again do (3 times arrow up):\ngit checkout HEAD^ -- /path/to/file\n\n\neffectively 'uncommitting':\nTo modify the last commit of the repository HEAD, obfuscating your accidentally pushed work, while potentially running into a conflict with your colleague who may have pulled it already, and who will grow grey hair and lose lots of time trying to reconcile his local branch head with the central one:\nTo remove file change from last commit:\n\nto revert the file to the state before the last commit, do:\ngit checkout HEAD^ /path/to/file\n\nto update the last commit with the reverted file, do:\ngit commit --amend\n\nto push the updated commit to the repo, do:\ngit push -f\n\n\nReally, consider using the preferred method mentioned before." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "How can I remove a file from Git within IntelliJ VCS?\nVCS has an Add option (Git Add) but seems to lack Git Remove.\nWhat's the idiomatic way to Git Remove with VCS?" }, { "role": "assistant", "content": "In the terminal, use git rm --cached -r .idea/.\nThis will remove the files from the GIT index, but leave the files locally." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "What's the difference between HEAD^ and HEAD~ in Git?\nWhen I specify an ancestor commit object in Git, I'm confused between HEAD^ and HEAD~.\nBoth have a \"numbered\" version like HEAD^3 and HEAD~2.\nThey seem very similar or the same to me, but are there any differences between the tilde and the caret?" }, { "role": "assistant", "content": "Rules of thumb\n\n<rev>~<n> goes backward n parents from rev, selecting the first parent each time.\nUse <rev>^<n> to select the n-th immediate parent of merge commit rev.\nUse ~ most of the time — to go back a number of generations and always choosing the first parent of merge commits, commonly what you want.\nUse ^ on merge commits — because they have two or more immediate parents.\nIn my experience, selecting a particular immediate parent of a merge commit by its index order, e.g., B^3, is rare. It’s also error-prone. Just use a hash when you can.\n\nMnemonics:\n\nTilde ~ is almost linear in appearance and wants to go backward in a straight line.\nCaret ^ suggests a merge commit: an interesting segment of a tree or a fork in the road.\n\nTilde\nThe “Specifying Revisions” section of the git rev-parse documentation defines ~ as\n\n<rev>~<n>, e.g. HEAD~, main~3\nA suffix ~<n> to a revision parameter means the commit object that is the nth generation ancestor of the named commit object, following only the first parents. For example, <rev>~3 is equivalent to <rev>^^^ which is equivalent to <rev>^1^1^1 …\n\nYou can get to parents of any commit anywhere in history. You can also move back through generations: for example, main~2 means the grandparent of the tip of the main branch, favoring the first parent on merge commits.\nCaret\nGit history is nonlinear: a directed acyclic graph (DAG) or tree. For a commit with only one parent, rev~ and rev^ mean the same thing. The caret selector becomes useful with merge commits because each one is the child of two or more parents — and strains language borrowed from biology.\nHEAD^ means the first immediate parent of the tip of the current branch (main in this example repository). HEAD^ is short for HEAD^1, and you can also address HEAD^2 and so on as appropriate. The same section of the git rev-parse documentation defines it as\n\n<rev>^, e.g. HEAD^, v1.5.1^0\nA suffix ^ to a revision parameter means the first parent of that commit object. ^<n> means the nth parent ([e.g.] <rev>^ is equivalent to <rev>^1). As a special rule, <rev>^0 means the commit itself and is used when <rev> is the object name of a tag object that refers to a commit object.\n\nExample from Git’s Documentation\nChain these specifiers or selectors arbitrarily, e.g., rev~3^2 in English is the second parent of the merge commit that is the great-grandparent (three generations back) of rev.\nThe aforementioned section of the git rev-parse documentation traces many paths through a notional git history in which time flows generally downward. Commits D, F, B, and A are merge commits.\n\nHere is an illustration, by Jon Loeliger. Both commit nodes B and C are parents of commit node A. Parent commits are ordered left-to-right.\nG H I J\n \\ / \\ /\n D E F\n \\ \| / \\\n \\ \| / \|\n \\\|/ \|\n B C\n \\ /\n \\ /\n A\n\nA = = A^0\nB = A^ = A^1 = A~1\nC = A^2\nD = A^^ = A^1^1 = A~2\nE = B^2 = A^^2\nF = B^3 = A^^3\nG = A^^^ = A^1^1^1 = A~3\nH = D^2 = B^^2 = A^^^2 = A~2^2\nI = F^ = B^3^ = A^^3^\nJ = F^2 = B^3^2 = A^^3^2\n\n\nRun the code below to create a git repository whose history matches the illustration’s structure and makes A the HEAD commit. The resulting SHA-1 hashes on your machine will match the ones in this answer.\n#! /usr/bin/env perl\n\nuse strict;\nuse warnings;\nuse subs qw/ postorder /;\nuse File::Temp qw/ mkdtemp /;\n\nmy %sha1;\nmy %parents = (\n A => [ qw/ B C / ],\n B => [ qw/ D E F / ],\n C => [ qw/ F / ],\n D => [ qw/ G H / ],\n F => [ qw/ I J / ],\n);\n\nsub postorder {\n my($root,$hash) = @_;\n my @parents = @{ $parents{$root} \|\| [] };\n postorder($_, $hash) for @parents;\n return if $sha1{$root};\n @parents = map \"-p $sha1{$_}\", @parents;\n chomp($sha1{$root} = `git commit-tree @parents -m \"$root\" $hash`);\n die \"$0: git commit-tree failed\" if $?;\n system(\"git tag '$root' '$sha1{$root}'\") == 0 or die \"$0: git tag failed\";\n}\n\n$0 =~ s!^./!!; # / fix Stack Overflow highlighting\nmy $repo = mkdtemp \"repoXXXXXXXX\";\nchdir $repo or die \"$0: chdir: $!\";\nsystem(\"git init\") == 0 or die \"$0: git init failed\";\nsystem(\"git config user.name 'Git User'\") == 0 or die \"$0: user.name failed\";\nsystem(\"git config user.email 'git.user\\@example.com'\") == 0 or die \"$0: user.email failed\";\nsystem(\"git config init.defaultBranch main\") == 0 or die \"$0: default branch failed\";\n\n$ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = 'Mon Oct 29 10:15:31 2018 +0900';\nchomp(my $tree = `git write-tree`); die \"$0: git write-tree failed\" if $?;\n\npostorder 'A', $tree;\nsystem \"git update-ref HEAD $sha1{A}\"; die \"$0: git update-ref failed\" if $?;\nsystem \"git update-ref main $sha1{A}\"; die \"$0: git update-ref failed\" if $?;\n\n# for browsing history - http://blog.kfish.org/2010/04/git-lola.html\nsystem \"git config alias.lol 'log --graph --decorate --pretty=oneline --abbrev-commit'\";\nsystem \"git config alias.lola 'log --graph --decorate --pretty=oneline --abbrev-commit --all'\";\n\nThe aliases in the new throwaway repo for git lol and git lola allow you to view history as below. git lol gives an ASCII-artish view of the current branch, and git lola does the same for all branches. In action:\n$ git lol\n 0a92ac1 (HEAD -> main, tag: A) A\n\|\\ \n\| * 00d2fb2 (tag: C) C\n\| \| \n\| \\ \n-. \| 75e7e8a (tag: B) B\n\|\\ \\\| \n\| \| f3fe76f (tag: F) F\n\| \| \|\\ \n\| \| \| * c193a93 (tag: J) J\n\| \| * 27c9a4e (tag: I) I\n\| * 63a46d4 (tag: E) E\n* d209203 (tag: D) D\n\|\\ \n\| * ff7985a (tag: H) H\n* 365f7d0 (tag: G) G\n\nThe output of git log shows child commits before their parents — or with time generally flowing upward, opposite to how it’s presented in the illustration. To make the output match the illustration, we’d like to toss in --reverse, but it isn’t compatible with --graph. In this case, a quick hack to reverse the lines of output with tac and flip the connectors in the graph makes time flow downward.\n$ git lol \| tr '.\\\\/' \"'/\\\\\\\\\" \| tac\n* 365f7d0 (tag: G) G\n\| * ff7985a (tag: H) H\n\|/ \n* d209203 (tag: D) D\n\| * 63a46d4 (tag: E) E\n\| \| * 27c9a4e (tag: I) I\n\| \| \| * c193a93 (tag: J) J\n\| \| \|/ \n\| \| * f3fe76f (tag: F) F\n\|/ /\| \n-' \| 75e7e8a (tag: B) B\n\| / \n\| \| \n\| 00d2fb2 (tag: C) C\n\|/ \n* 0a92ac1 (HEAD -> main, tag: A) A\n\nThe tags allow you to address commits by the same names from the illustration and check your understanding with git describe.\n$ git describe A^\nB\n$ git describe A~^3~\nI\n$ git describe A~^3^2\nJ\n$ git describe A^2~\nF\n\nWe can even validate the illustration.\n#! /usr/bin/env perl\n\nuse strict;\nuse warnings;\n\nmy $verbose = 0;\nmy $pass = 1;\n\nwhile (<DATA>) {\n chomp;\n my($commit,@revs) = split /\\s+=(?:\\s+=)*\\s+/;\n my $result = \"$commit:\\n\"; \n foreach my $rev (@revs) {\n my $status = \"OK\";\n chomp(my $describe = `git describe '$rev' 2>&1`);\n $status = \"FAIL - [$describe]\" unless $describe eq $commit;\n $result .= sprintf(\" - %-7s (%s)\\n\", $rev, $status);\n $pass = 0 unless $status eq \"OK\";\n }\n print $result if $verbose or $result =~ /FAIL/;\n}\nprint $pass ? \"PASS\\n\" : \"FAIL\\n\";\n__DATA__\nA = = A^0\nB = A^ = A^1 = A~1\nC = A^2\nD = A^^ = A^1^1 = A~2\nE = B^2 = A^^2\nF = B^3 = A^^3\nG = A^^^ = A^1^1^1 = A~3\nH = D^2 = B^^2 = A^^^2 = A~2^2\nI = F^ = B^3^ = A^^3^\nJ = F^2 = B^3^2 = A^^3^2\n\nThe “Specifying Revisions” in the git rev-parse documentation is full of great information and is worth an in-depth read. See also Git Tools - Revision Selection from the book Pro Git.\nOrder of Parent Commits\nIn practice, treat parents’ order as arbitrary and query a merge commit’s metadata as below.\nIn our example repository, commit A is a merge commit. We know this because it has multiple immediate parents. The Merge header in the output of git show A displays its parents’ object names or hashes.\ncommit 0a92ac13d0abe16fc74d0b4c6fa67326fdbc112c\nMerge: 75e7e8a 00d2fb2\nAuthor: Git User <[email protected]>\nDate: Mon Oct 29 10:15:31 2018 +0900\n\n A\n\nWe can confirm the ordering by asking git rev-parse to show the immediate parents of A in sequence.\n$ git rev-parse A^1 A^2\n75e7e8acabbf65d63c0525d95fe529730771e7a2\n00d2fb266838e6111e68ab3bbce5c0b9f1035ec9\n\nQuerying the non-existent third parent of A results in an error.\n$ git rev-parse A^3\nA^3\nfatal: ambiguous argument 'A^3': unknown revision or path not in the working tree.\nUse '--' to separate paths from revisions, like this:\n'git <command> [<revision>...] -- [<file>...]'\n\nIf you want to extract the parents only, use pretty format %P for the full hashes\n$ git log -1 --pretty=%P A\n75e7e8acabbf65d63c0525d95fe529730771e7a2 00d2fb266838e6111e68ab3bbce5c0b9f1035ec9\n\nor %p for abbreviated hashes\n$ git log -1 --pretty=%p A\n75e7e8a 00d2fb2\n\nor the ^@ suffix with git rev-parse as in\n$ git rev-parse A^@\n75e7e8acabbf65d63c0525d95fe529730771e7a2\n00d2fb266838e6111e68ab3bbce5c0b9f1035ec9" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "git-config - Get and set repository or global options sendemail.smtpBatchSize" }, { "role": "assistant", "content": "Number of messages to be sent per connection, after that a relogin\nwill happen. If the value is 0 or undefined, send all messages in\none connection.\nSee also the --batch-size option of git-send-email ." } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Can't update: no tracked branch\n\nI am on Android Studio (Preview) 0.6.0 on Windows and was trying to share my project on GitHub. I used Git Shell to initialize, add, commit and push the project to GitHub. But when I tried to update my project from within Android Studio , I got this error:\nCan't update: no tracked branch\nNo tracked branch configured for branch master.\nTo make your branch track a remote branch call, for example,\ngit branch --set-upstream master origin/master\n\nIt does provide this suggestion but I am not sure what to do at this point. Is there a way to fix this from within Android Studio?" }, { "role": "assistant", "content": "If I'm not mislead, you just need to set your local branches to track their pairs in the origin server.\nUsing your command line, you can try \ngit checkout mybranch\ngit branch --set-upstream-to=origin/mybranch\n\nThat will configure something as an equivalent of your local branch in the server. I'll bet that Android Studio is complaining about the lack of that.\nIf someone knows how to do this using the GUI of that IDE, that would be interesting to read. :)" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "When to use \"chore\" as type of commit message? [closed]\nClosed. This question is opinion-based. 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 can be answered with facts and citations by editing this post.\n\n\nClosed 10 months ago.\n\n\nThe community reviewed whether to reopen this question 10 months ago and left it closed:\n\nOriginal close reason(s) were not resolved\n\n\n\n\n\n\n Improve this question\n \n\n\n\nWhat is the use of chore in semantic version control commit messages? Other types like feat or fix are clear, but I don't know when to use \"chore\".\nCan anyone provide a couple of examples of its use?\nAnother maybe not related question: What's the proper type of commit messages for modifying files like .gitignore?" }, { "role": "assistant", "content": "You can see a short definition in \"Git Commit Msg\":\n\nchore: updating grunt tasks etc; no production code change\n\nIt is used in:\n\n\"Semantic Commit Messages\" and in\n\nthe project \"fteem/git-semantic-commits\".\n git chore \"commit-message-here\" -> git commit -m 'chore: commit-message-here' \n\n\n\nModifying the .gitignore would be part of the \"chores\".\n\"grunt task\" means nothing that an external user would see:\n\nimplementation (of an existing feature, which doesn't involve a fix),\nconfiguration (like the .gitignore or .gitattributes),\nprivate internal methods...\n\nAlthough Owen S mentions in the comments:\n\nLooking at the Karma page you link to, I suspect that grunt task may refer specifically to Javascript's build tool grunt.\nIn which case, they probably didn't have in mind changes involving implementation or private internal methods, but rather tool changes, configuration changes, and changes to things that do not actually go into production at all.\n(Our shop currently uses it for those, and also for simple refactoring.)" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Python Git Module experiences? [closed]\nClosed. This question is opinion-based. 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 can be answered with facts and citations by editing this post.\n\n\nClosed 10 years ago.\n\n\nThe community reviewed whether to reopen this question 2 years ago and left it closed:\n\nOriginal close reason(s) were not resolved\n\n\n\n\n\n\n Improve this question\n \n\n\n\nWhat are people's experiences with any of the Git modules for Python? (I know of GitPython, PyGit, and Dulwich - feel free to mention others if you know of them.)\nI am writing a program which will have to interact (add, delete, commit) with a Git repository, but have no experience with Git, so one of the things I'm looking for is ease of use/understanding with regards to Git.\nThe other things I'm primarily interested in are maturity and completeness of the library, a reasonable lack of bugs, continued development, and helpfulness of the documentation and developers.\nIf you think of something else I might want/need to know, please feel free to mention it." }, { "role": "assistant", "content": "While this question was asked a while ago and I don't know the state of the libraries at that point, it is worth mentioning for searchers that GitPython does a good job of abstracting the command line tools so that you don't need to use subprocess. There are some useful built in abstractions that you can use, but for everything else you can do things like:\nimport git\nrepo = git.Repo( '/home/me/repodir' )\nprint repo.git.status()\n# checkout and track a remote branch\nprint repo.git.checkout( 'origin/somebranch', b='somebranch' )\n# add a file\nprint repo.git.add( 'somefile' )\n# commit\nprint repo.git.commit( m='my commit message' )\n# now we are one commit ahead\nprint repo.git.status()\n\nEverything else in GitPython just makes it easier to navigate. I'm fairly well satisfied with this library and appreciate that it is a wrapper on the underlying git tools.\nUPDATE: I've switched to using the sh module for not just git but most commandline utilities I need in python. To replicate the above I would do this instead:\nimport sh\ngit = sh.git.bake(_cwd='/home/me/repodir')\nprint git.status()\n# checkout and track a remote branch\nprint git.checkout('-b', 'somebranch')\n# add a file\nprint git.add('somefile')\n# commit\nprint git.commit(m='my commit message')\n# now we are one commit ahead\nprint git.status()" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Git checkout - switching back to HEAD\nI've been doing my project while at some point I discovered that one thing stopped working. I needed to look up the state of my code when it was working correctly, so I've decided to use git checkout (because I wanted to check-something-out). And so I've done\ngit checkout SHA\n\ncouple times while going back to point from which I can't go to HEAD, the output is following:\ngit checkout SHA-HEAD\n\nerror: Your local changes to the following files would be overwritten by checkout:\n [list of files]\nPlease, commit your changes or stash them before you can switch branches.\nAborting\n\nI am pretty much sure I have NOT changed anything. The command\ngit checkout master\n\ngives the same output.\nIs there a way to go back to HEAD?\nWhat is the safe way of \"jumping over\" history commits?" }, { "role": "assistant", "content": "You can stash (save the changes in temporary place) then, back to master branch HEAD.\n$ git add .\n$ git stash\n$ git checkout master\n\nNote that some sites have changed the name of the default branch from \"master\" to \"main\" so you might have to use git checkout main instead.\n\nJump Over Commits Back and Forth:\n\nGo to a specific commit-sha.\n $ git checkout <commit-sha>\n\n\nIf you have uncommitted changes here then, you can checkout to a new branch \| Add \| Commit \| Push the current branch to the remote.\n # checkout a new branch, add, commit, push\n $ git checkout -b <branch-name>\n $ git add .\n $ git commit -m 'Commit message'\n $ git push origin HEAD # push the current branch to remote \n\n $ git checkout master # back to master branch now\n\n\nIf you have changes in the specific commit and don't want to keep the changes, you can do stash or reset then checkout to master (or, any other branch).\n # stash\n $ git add -A\n $ git stash\n $ git checkout master\n\n # reset\n $ git reset --hard HEAD\n $ git checkout master\n\n\nAfter checking out a specific commit if you have no uncommitted change(s) then, just back to master or other branch.\n $ git status # see the changes\n $ git checkout master\n\n # or, shortcut\n $ git checkout - # back to the previous state" } ]
[ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Git rebase (Merge Squash) my feature branch onto another branch\nI'm looking for a git command to help me with my feature branches when they're ready to go into Master. This git command would squash all my changes on my branch into a single commit on top of master. I do this today with:\ngit rebase origin/master\ngit rebase -i HEAD~4\n\nWhere 4 is the number of commits to squash. However, this requires me to know how many commits I have. I do this today by running:\ngit log HEAD...origin/master\n\nand then counting the commits.\nI feel as though there should be a better way to do this. Or is this how everyone else does it, too?" }, { "role": "assistant", "content": "All you have to do is:\ngit checkout feature_branch\ngit rebase master\ngit checkout master\ngit merge --squash feature_branch\n\nAs the docs for git merge --squash say:\n\nProduce the working tree and index state as if a real merge happened (except for the merge information), but do not actually make a commit or move the HEAD, nor record $GIT_DIR/MERGE_HEAD to cause the next git commit command to create a merge commit. This allows you to create a single commit on top of the current branch whose effect is the same as merging another branch (or more in case of an octopus).\n\nAfter that, you can git commit your changes which are already staged." } ]

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.