diff options
| -rw-r--r-- | community/weblogs/tschwinge/2009-06-24_importing_from_gnu_arch_into_git.mdwn | 96 |
1 files changed, 96 insertions, 0 deletions
diff --git a/community/weblogs/tschwinge/2009-06-24_importing_from_gnu_arch_into_git.mdwn b/community/weblogs/tschwinge/2009-06-24_importing_from_gnu_arch_into_git.mdwn new file mode 100644 index 00000000..94de71b8 --- /dev/null +++ b/community/weblogs/tschwinge/2009-06-24_importing_from_gnu_arch_into_git.mdwn @@ -0,0 +1,96 @@ +[[!meta copyright="Copyright © 2009 Free Software Foundation, Inc."]] + +[[!meta license="""[[!toggle id="license" text="GFDL 1.2+"]][[!toggleable +id="license" text="Permission is granted to copy, distribute and/or modify this +document under the terms of the GNU Free Documentation License, Version 1.2 or +any later version published by the Free Software Foundation; with no Invariant +Sections, no Front-Cover Texts, and no Back-Cover Texts. A copy of the license +is included in the section entitled [[GNU Free Documentation +License|/fdl]]."]]"""]] + +[[!meta title="converting from GNU arch to Git -- without direct repository +access"]] + +I wanted to import an old GNU arch repository into Git, but only had HTTP +access via ArchZoom. I spent quite some time to try teaching `git archimport` +to use HTTP access to that repository, but this didn't work out. Too bad -- +but at least, using ArchZoom, I was able to get the individual revisions' +tarballs: + + $ ls -1 *.tar.gz + bpf--devel--0.0--base-0.tar.gz + bpf--devel--0.0--patch-1.tar.gz + bpf--devel--0.0--patch-10.tar.gz + bpf--devel--0.0--patch-11.tar.gz + bpf--devel--0.0--patch-12.tar.gz + bpf--devel--0.0--patch-2.tar.gz + bpf--devel--0.0--patch-3.tar.gz + [...] + bpf--devel--0.0--patch-9.tar.gz + bpf--release--0.1--base-0.tar.gz + bpf--release--0.1--patch-1.tar.gz + bpf--release--0.1--patch-2.tar.gz + [...] + bpf--release--0.1--patch-8.tar.gz + +I unpacked these: + + $ for f in *.tar.gz; do tar -xz < "$f" || echo >&2 "$f" failed; done + +The last revision's tree apparently contains all previous revisions' commit +information (author, date, message), so use that: + + $ cp -a ↩ + bpf--release--0.1--patch-8/{arch}/bpf/bpf--devel/bpf--devel--0.0/info@hurdfr.org--hurdfr/patch-log ↩ + d-patch-log + $ cp -a ↩ + bpf--release--0.1--patch-8/{arch}/bpf/bpf--release/bpf--release--0.1/info@hurdfr.org--hurdfr/patch-log ↩ + r-patch-log + +... and extract the information that we need: + + $ base=bpf--devel--0.0-- && ↩ + for f in d-patch-log/*; do ↩ + grep < "$f" ^Creator: | head -n 1 ↩ + | { read j c && ↩ + echo "$c" | sed s%' <.*'%% ↩ + > "$base""$(basename "$f")".author_name && ↩ + echo "$c" | sed -e 's%.*<%%' -e 's%>.*%%' ↩ + > "$base""$(basename "$f")".author_email; } && ↩ + grep < "$f" ^Standard-date: | head -n 1 | { read j d && echo "$d" ↩ + > "$base""$(basename "$f")".author_date; } && ↩ + { grep < "$f" ^Summary: | head -n 1 | { read j m && echo "$m"; } && ↩ + echo && sed < "$f" '1,/^$/d'; } ↩ + > "$base""$(basename "$f")".log ↩ + || echo >&2 "$f" failed; ↩ + done + $ base=bpf--release--0.1-- && ↩ + for f in r-patch-log/*; [...] + +(Of course, I could have used something more elaborate than shell scripting...) + +Remove the GNU arch stuff that we don't need anymore: + + $ find bpf--*/ -type d \( -name {arch} -o -name .arch-ids \) -print0 ↩ + | xargs -0 rm -r + +The `base-0` revisions are actually either empty (the `devel` one) or +equivalent to the previous revision (the `release` one), so remove these: + + $ rm -rf bpf--devel--0.0--base-0 bpf--release--0.1--base-0 + +Finally, import all the other ones: + + $ mkdir g && ( cd g/ && git init ) + $ for d in bpf--d*-? bpf--d*-?? bpf--r*; do ↩ + test -d "$d"/ || continue && ↩ + ( cd g/ && ↩ + rsync -a --delete --exclude=/.git ../"$d"/ ./ && ↩ + git add . && ↩ + GIT_AUTHOR_NAME="$(cat ../"$d".author_name)" ↩ + GIT_AUTHOR_EMAIL="$(cat ../"$d".author_email)" ↩ + GIT_AUTHOR_DATE="$(cat ../"$d".author_date)" ↩ + git commit -F ../"$d".log -a ); ↩ + done + +Voilà! |