git.list-big_files.txt Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of resources
The newest version!
# http://naleid.com/blog/2012/01/17/finding-and-purging-big-files-from-git-history

# What object SHA is associated with each file in the Repo?
git rev-list --objects --all | sort -k 2 > allfileshas.txt

# Get the last object SHA for all committed files and sort them in biggest to smallest order:
git gc && git verify-pack -v .git/objects/pack/pack-*.idx | egrep "^\w+ blob\W+[0-9]+ [0-9]+ [0-9]+$" | sort -k 3 -n -r > bigobjects.txt

# In case we are in a bare repo (with --mirror)
git gc && git verify-pack -v objects/pack/pack-*.idx | egrep "^\w+ blob\W+[0-9]+ [0-9]+ [0-9]+$" | sort -k 3 -n -r > bigobjects.txt

for SHA in `cut -f 1 -d\  < bigobjects.txt`; do
	echo $(grep $SHA bigobjects.txt) $(grep $SHA allfileshas.txt) | awk '{print $1,$3,$7}' >> bigtosmall.txt
done;

less bigtosmall.txt


---------------------------------------
http://dalibornasevic.com/posts/2-permanently-remove-files-and-folders-from-git-repo
http://stackoverflow.com/questions/28720151/git-gc-aggressive-vs-git-repack
// http://stackoverflow.com/questions/1904860/how-to-remove-unreferenced-blobs-from-my-git-repo
git remote rm origin
rm -rf .git/refs/original/ .git/refs/remotes/ .git/*_HEAD .git/logs/

# Remove safety references as they refers to removed objects
git for-each-ref --format="%(refname)" refs/original/ | xargs -n1 --no-run-if-empty git update-ref -d

git reflog expire --expire=now --all && git gc --prune=now --aggressive
git -c gc.reflogExpire=0 -c gc.reflogExpireUnreachable=0 -c gc.rerereresolved=0 -c gc.rerereunresolved=0 -c gc.pruneExpire=now gc "$@"

git push origin --force --all
git push origin --force --tags
---------------------------------------------------


# Purging a file or directory from history
git filter-branch --prune-empty --index-filter "
git rm -rf --cached --ignore-unmatch top/sub
git rm -rf --cached --ignore-unmatch 'prefix[0-9]*'
" --tag-name-filter cat -- --all



# Then clone the repo and make sure to not leave any hard links with:
# git clone --no-hardlinks file:///Users/yourUser/your/full/repo/path repo-clone-name
git clone --no-hardlinks ./try2/ try3

# Checkfile consumption with
git count-objects -vH

------------------------------------
With BFG
(referred by https://git-scm.com/docs/git-filter-branch)
https://rtyley.github.io/bfg-repo-cleaner/

# First clone a fresh copy of your repo, using the --mirror flag
git clone --mirror git://example.com/some-big-repo.git

# Delete all files named 'id_rsa' or 'id_dsa'
java -jar bfg.jar --delete-files id_{dsa,rsa}  my-repo.git

# Remove all folders or files named 'target'
java -jar bfg-1.12.13.jar --delete-folders target --no-blob-protection  my-repo.git

-------------------------------------

Full script:


git clone --mirror git://example.com/some-big-repo.git

java -jar bfg-1.12.13.jar --delete-files id_{dsa,rsa} --no-blob-protection my-repo.git
java -jar bfg-1.12.13.jar --delete-folders target --no-blob-protection my-repo.git

git reflog expire --expire=now --all && git gc --prune=now --aggressive

git filter-branch -f --prune-empty --index-filter '
git rm -rf --cached --ignore-unmatch folder/subFolder && 
git rm -rf --cached --ignore-unmatch anotherFolder
' --tag-name-filter cat -- --all