summaryrefslogtreecommitdiff
path: root/Documentation
diff options
context:
space:
mode:
Diffstat (limited to 'Documentation')
-rw-r--r--Documentation/.gitignore1
-rw-r--r--Documentation/Makefile18
-rw-r--r--Documentation/RelNotes-1.6.5.4.txt32
-rw-r--r--Documentation/RelNotes-1.6.5.5.txt49
-rw-r--r--Documentation/RelNotes-1.6.5.6.txt23
-rw-r--r--Documentation/RelNotes-1.6.5.7.txt19
-rw-r--r--Documentation/RelNotes-1.6.6.1.txt15
-rw-r--r--Documentation/RelNotes-1.6.6.txt181
-rw-r--r--Documentation/RelNotes-1.7.0.txt70
-rw-r--r--Documentation/SubmittingPatches14
-rw-r--r--Documentation/config.txt58
-rw-r--r--Documentation/date-formats.txt26
-rw-r--r--Documentation/git-add.txt57
-rw-r--r--Documentation/git-archive.txt5
-rw-r--r--Documentation/git-bisect-lk2009.txt1358
-rw-r--r--Documentation/git-bisect.txt5
-rw-r--r--Documentation/git-bundle.txt2
-rw-r--r--Documentation/git-clone.txt2
-rw-r--r--Documentation/git-commit-tree.txt1
-rw-r--r--Documentation/git-commit.txt28
-rw-r--r--Documentation/git-config.txt14
-rw-r--r--Documentation/git-cvsserver.txt15
-rw-r--r--Documentation/git-fast-import.txt6
-rw-r--r--Documentation/git-mailinfo.txt7
-rw-r--r--Documentation/git-push.txt4
-rw-r--r--Documentation/git-remote-helpers.txt28
-rw-r--r--Documentation/git-reset.txt1
-rw-r--r--Documentation/git-rm.txt60
-rw-r--r--Documentation/git-send-email.txt13
-rw-r--r--Documentation/git-status.txt90
-rw-r--r--Documentation/git-upload-pack.txt2
-rw-r--r--Documentation/git.txt11
-rw-r--r--Documentation/gitattributes.txt19
-rw-r--r--Documentation/gitcore-tutorial.txt2
-rw-r--r--Documentation/githooks.txt29
-rw-r--r--Documentation/manpage-base-url.xsl.in10
-rw-r--r--Documentation/pretty-formats.txt8
-rw-r--r--Documentation/technical/api-hash.txt50
-rw-r--r--Documentation/technical/api-strbuf.txt10
39 files changed, 2176 insertions, 167 deletions
diff --git a/Documentation/.gitignore b/Documentation/.gitignore
index d8edd90..1c3a9fe 100644
--- a/Documentation/.gitignore
+++ b/Documentation/.gitignore
@@ -8,3 +8,4 @@ gitman.info
howto-index.txt
doc.dep
cmds-*.txt
+manpage-base-url.xsl
diff --git a/Documentation/Makefile b/Documentation/Makefile
index cd5b439..4797b2d 100644
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -17,6 +17,7 @@ DOC_HTML=$(MAN_HTML)
ARTICLES = howto-index
ARTICLES += everyday
ARTICLES += git-tools
+ARTICLES += git-bisect-lk2009
# with their own formatting rules.
SP_ARTICLES = howto/revert-branch-rebase howto/using-merge-subtree user-manual
API_DOCS = $(patsubst %.txt,%,$(filter-out technical/api-index-skel.txt technical/api-index.txt, $(wildcard technical/api-*.txt)))
@@ -103,6 +104,17 @@ ifdef DOCBOOK_SUPPRESS_SP
XMLTO_EXTRA += -m manpage-suppress-sp.xsl
endif
+# Newer DocBook stylesheet emits warning cruft in the output when
+# this is not set, and if set it shows an absolute link. Older
+# stylesheets simply ignore this parameter.
+#
+# Distros may want to use MAN_BASE_URL=file:///path/to/git/docs/
+# or similar.
+ifndef MAN_BASE_URL
+MAN_BASE_URL = file://$(htmldir)/
+endif
+XMLTO_EXTRA += -m manpage-base-url.xsl
+
# If your target system uses GNU groff, it may try to render
# apostrophes as a "pretty" apostrophe using unicode. This breaks
# cut&paste, so you should set GNU_ROFF to force them to be ASCII
@@ -230,6 +242,7 @@ clean:
$(RM) howto-index.txt howto/*.html doc.dep
$(RM) technical/api-*.html technical/api-index.txt
$(RM) $(cmds_txt) *.made
+ $(RM) manpage-base-url.xsl
$(MAN_HTML): %.html : %.txt
$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
@@ -237,7 +250,10 @@ $(MAN_HTML): %.html : %.txt
$(ASCIIDOC_EXTRA) -agit_version=$(GIT_VERSION) -o $@+ $< && \
mv $@+ $@
-%.1 %.5 %.7 : %.xml
+manpage-base-url.xsl: manpage-base-url.xsl.in
+ sed "s|@@MAN_BASE_URL@@|$(MAN_BASE_URL)|" $< > $@
+
+%.1 %.5 %.7 : %.xml manpage-base-url.xsl
$(QUIET_XMLTO)$(RM) $@ && \
xmlto -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
diff --git a/Documentation/RelNotes-1.6.5.4.txt b/Documentation/RelNotes-1.6.5.4.txt
new file mode 100644
index 0000000..e42f8b2
--- /dev/null
+++ b/Documentation/RelNotes-1.6.5.4.txt
@@ -0,0 +1,32 @@
+Git v1.6.5.4 Release Notes
+==========================
+
+Fixes since v1.6.5.3
+--------------------
+
+ * "git help" (without argument) used to check if you are in a directory
+ under git control. There was no breakage in behaviour per-se, but this
+ was unnecessary.
+
+ * "git prune-packed" gave progress output even when its standard error is
+ not connected to a terminal; this caused cron jobs that run it to
+ produce crufts.
+
+ * "git pack-objects --all-progress" is an option to ask progress output
+ from write-object phase _if_ progress output were to be produced, and
+ shouldn't have forced the progress output.
+
+ * "git apply -p<n> --directory=<elsewhere>" did not work well for a
+ non-default value of n.
+
+ * "git merge foo HEAD" was misparsed as an old-style invocation of the
+ command and produced a confusing error message. As it does not specify
+ any other branch to merge, it shouldn't be mistaken as such. We will
+ remove the old style "git merge <message> HEAD <commit>..." syntax in
+ future versions, but not in this release,
+
+ * "git merge -m <message> <branch>..." added the standard merge message
+ on its own after user-supplied message, which should have overrided the
+ standard one.
+
+Other minor documentation updates are included.
diff --git a/Documentation/RelNotes-1.6.5.5.txt b/Documentation/RelNotes-1.6.5.5.txt
new file mode 100644
index 0000000..ecfc57d
--- /dev/null
+++ b/Documentation/RelNotes-1.6.5.5.txt
@@ -0,0 +1,49 @@
+Git v1.6.5.5 Release Notes
+==========================
+
+Fixes since v1.6.5.4
+--------------------
+
+ * Manual pages can be formatted with older xmlto again.
+
+ * GREP_OPTIONS exported from user's environment could have broken
+ our scripted commands.
+
+ * In configuration files, a few variables that name paths can begin with
+ ~/ and ~username/ and they are expanded as expected. This is not a
+ bugfix but 1.6.6 will have this and without backporting users cannot
+ easily use the same ~/.gitconfig across versions.
+
+ * "git diff -B -M" did the same computation to hash lines of contents
+ twice, and held onto memory after it has used the data in it
+ unnecessarily before it freed.
+
+ * "git diff -B" and "git diff --dirstat" was not counting newly added
+ contents correctly.
+
+ * "git format-patch revisions... -- path" issued an incorrect error
+ message that suggested to use "--" on the command line when path
+ does not exist in the current work tree (it is a separate matter if
+ it makes sense to limit format-patch with pathspecs like that
+ without using the --full-diff option).
+
+ * "git grep -F -i StRiNg" did not work as expected.
+
+ * Enumeration of available merge strategies iterated over the list of
+ commands in a wrong way, sometimes producing an incorrect result.
+
+ * "git shortlog" did not honor the "encoding" header embedded in the
+ commit object like "git log" did.
+
+ * Reading progress messages that come from the remote side while running
+ "git pull" is given precedence over reading the actual pack data to
+ prevent garbled progress message on the user's terminal.
+
+ * "git rebase" got confused when the log message began with certain
+ strings that looked like Subject:, Date: or From: header.
+
+ * "git reset" accidentally run in .git/ directory checked out the
+ work tree contents in there.
+
+
+Other minor documentation updates are included.
diff --git a/Documentation/RelNotes-1.6.5.6.txt b/Documentation/RelNotes-1.6.5.6.txt
new file mode 100644
index 0000000..a9eaf76
--- /dev/null
+++ b/Documentation/RelNotes-1.6.5.6.txt
@@ -0,0 +1,23 @@
+Git v1.6.5.6 Release Notes
+==========================
+
+Fixes since v1.6.5.5
+--------------------
+
+ * "git add -p" had a regression since v1.6.5.3 that broke deletion of
+ non-empty files.
+
+ * "git archive -o o.zip -- Makefile" produced an archive in o.zip
+ but in POSIX tar format.
+
+ * Error message given to "git pull --rebase" when the user didn't give
+ enough clue as to what branch to integrate with still talked about
+ "merging with" the branch.
+
+ * Error messages given by "git merge" when the merge resulted in a
+ fast-forward still were in plumbing lingo, even though in v1.6.5
+ we reworded messages in other cases.
+
+ * The post-upload-hook run by upload-pack in response to "git fetch" has
+ been removed, due to security concerns (the hook first appeared in
+ 1.6.5).
diff --git a/Documentation/RelNotes-1.6.5.7.txt b/Documentation/RelNotes-1.6.5.7.txt
new file mode 100644
index 0000000..5b49ea5
--- /dev/null
+++ b/Documentation/RelNotes-1.6.5.7.txt
@@ -0,0 +1,19 @@
+Git v1.6.5.7 Release Notes
+==========================
+
+Fixes since v1.6.5.6
+--------------------
+
+* If a user specifies a color for a <slot> (i.e. a class of things to show
+ in a particular color) that is known only by newer versions of git
+ (e.g. "color.diff.func" was recently added for upcoming 1.6.6 release),
+ an older version of git should just ignore them. Instead we diagnosed
+ it as an error.
+
+* With help.autocorrect set to non-zero value, the logic to guess typoes
+ in the subcommand name misfired and ran a random nonsense command.
+
+* If a command is run with an absolute path as a pathspec inside a bare
+ repository, e.g. "rev-list HEAD -- /home", the code tried to run
+ strlen() on NULL, which is the result of get_git_work_tree(), and
+ segfaulted.
diff --git a/Documentation/RelNotes-1.6.6.1.txt b/Documentation/RelNotes-1.6.6.1.txt
new file mode 100644
index 0000000..4c88beb
--- /dev/null
+++ b/Documentation/RelNotes-1.6.6.1.txt
@@ -0,0 +1,15 @@
+Git v1.6.6.1 Release Notes
+==========================
+
+Fixes since v1.6.6
+------------------
+
+ * http-backend was not listed in the command list in the documentation.
+
+Other minor documentation updates are included.
+
+--
+exec >/var/tmp/1
+O=v1.6.6-4-gd828fdb
+echo O=$(git describe maint)
+git shortlog --no-merges $O..maint
diff --git a/Documentation/RelNotes-1.6.6.txt b/Documentation/RelNotes-1.6.6.txt
index 371101d..04e205c 100644
--- a/Documentation/RelNotes-1.6.6.txt
+++ b/Documentation/RelNotes-1.6.6.txt
@@ -1,48 +1,123 @@
Git v1.6.6 Release Notes
========================
-In this release, "git fsck" defaults to "git fsck --full" and checks
-packfiles, and because of this it will take much longer to complete
-than before. If you prefer a quicker check only on loose objects (the
-old default), you can say "git fsck --no-full". This has been
-supported by 1.5.4 and newer versions of git, so it is safe to write
-it in your script even if you use slightly older git on some of your
-machines.
+Notes on behaviour change
+-------------------------
+
+ * In this release, "git fsck" defaults to "git fsck --full" and
+ checks packfiles, and because of this it will take much longer to
+ complete than before. If you prefer a quicker check only on loose
+ objects (the old default), you can say "git fsck --no-full". This
+ has been supported by 1.5.4 and newer versions of git, so it is
+ safe to write it in your script even if you use slightly older git
+ on some of your machines.
+
+Preparing yourselves for compatibility issues in 1.7.0
+------------------------------------------------------
+
+In git 1.7.0, which is planned to be the release after 1.6.6, there will
+be a handful of behaviour changes that will break backward compatibility.
+
+These changes were discussed long time ago and existing behaviours have
+been identified as more problematic to the userbase than keeping them for
+the sake of backward compatibility.
+
+When necessary, a transition strategy for existing users has been designed
+not to force them running around setting configuration variables and
+updating their scripts in order to either keep the traditional behaviour
+or adjust to the new behaviour, on the day their sysadmin decides to install
+the new version of git. When we switched from "git-foo" to "git foo" in
+1.6.0, even though the change had been advertised and the transition
+guide had been provided for a very long time, the users procrastinated
+during the entire transtion period, and ended up panicking on the day
+their sysadmins updated their git installation. We are trying to avoid
+repeating that unpleasantness in the 1.7.0 release.
+
+For changes decided to be in 1.7.0, commands that will be affected
+have been much louder to strongly discourage such procrastination, and
+they continue to be in this release. If you have been using recent
+versions of git, you would have seen warnings issued when you used
+features whose behaviour will change, with a clear instruction on how
+to keep the existing behaviour if you want to. You hopefully are
+already well prepared.
+
+Of course, we have also been giving "this and that will change in
+1.7.0; prepare yourselves" warnings in the release notes and
+announcement messages for the past few releases. Let's see how well
+users will fare this time.
+
+ * "git push" into a branch that is currently checked out (i.e. pointed by
+ HEAD in a repository that is not bare) will be refused by default.
+
+ Similarly, "git push $there :$killed" to delete the branch $killed
+ in a remote repository $there, when $killed branch is the current
+ branch pointed at by its HEAD, will be refused by default.
+
+ Setting the configuration variables receive.denyCurrentBranch and
+ receive.denyDeleteCurrent to 'ignore' in the receiving repository
+ can be used to override these safety features. Versions of git
+ since 1.6.2 have issued a loud warning when you tried to do these
+ operations without setting the configuration, so repositories of
+ people who still need to be able to perform such a push should
+ already have been future proofed.
+
+ Please refer to:
+
+ http://git.or.cz/gitwiki/GitFaq#non-bare
+ http://thread.gmane.org/gmane.comp.version-control.git/107758/focus=108007
+
+ for more details on the reason why this change is needed and the
+ transition process that already took place so far.
+
+ * "git send-email" will not make deep threads by default when sending a
+ patch series with more than two messages. All messages will be sent
+ as a reply to the first message, i.e. cover letter. Git 1.6.6 (this
+ release) will issue a warning about the upcoming default change, when
+ it uses the traditional "deep threading" behaviour as the built-in
+ default. To squelch the warning but still use the "deep threading"
+ behaviour, give --chain-reply-to option or set sendemail.chainreplyto
+ to true.
+
+ It has been possible to configure send-email to send "shallow thread"
+ by setting sendemail.chainreplyto configuration variable to false.
+ The only thing 1.7.0 release will do is to change the default when
+ you haven't configured that variable.
+
+ * "git status" will not be "git commit --dry-run". This change does not
+ affect you if you run the command without pathspec.
+
+ Nobody sane found the current behaviour of "git status Makefile" useful
+ nor meaningful, and it confused users. "git commit --dry-run" has been
+ provided as a way to get the current behaviour of this command since
+ 1.6.5.
+
+ * "git diff" traditionally treated various "ignore whitespace" options
+ only as a way to filter the patch output. "git diff --exit-code -b"
+ exited with non-zero status even if all changes were about changing the
+ ammount of whitespace and nothing else. and "git diff -b" showed the
+ "diff --git" header line for such a change without patch text.
+
+ In 1.7.0, the "ignore whitespaces" will affect the semantics of the
+ diff operation itself. A change that does not affect anything but
+ whitespaces will be reported with zero exit status when run with
+ --exit-code, and there will not be "diff --git" header for such a
+ change.
-In git 1.7.0, which is planned to be the release after 1.6.6, "git
-push" into a branch that is currently checked out will be refused by
-default.
-
-You can choose what should happen upon such a push by setting the
-configuration variable receive.denyCurrentBranch in the receiving
-repository.
-
-Also, "git push $there :$killed" to delete the branch $killed in a remote
-repository $there, when $killed branch is the current branch pointed at by
-its HEAD, will be refused by default.
-
-You can choose what should happen upon such a push by setting the
-configuration variable receive.denyDeleteCurrent in the receiving
-repository.
-
-To ease the transition plan, the receiving repository of such a
-push running this release will issue a big warning when the
-configuration variable is missing. Please refer to:
-
- http://git.or.cz/gitwiki/GitFaq#non-bare
- http://thread.gmane.org/gmane.comp.version-control.git/107758/focus=108007
-
-for more details on the reason why this change is needed and the
-transition plan.
Updates since v1.6.5
--------------------
(subsystems)
- * various git-gui updates including new translations, wm states, etc.
+ * various gitk updates including use of themed widgets under Tk 8.5,
+ Japanese translation, a fix to a bug when running "gui blame" from
+ a subdirectory, etc.
+
+ * various git-gui updates including new translations, wm states fixes,
+ Tk bug workaround after quitting, improved heuristics to trigger gc,
+ etc.
- * git-svn updates.
+ * various git-svn updates.
* "git fetch" over http learned a new mode that is different from the
traditional "dumb commit walker".
@@ -71,11 +146,25 @@ Updates since v1.6.5
is only one remote tracking branch "frotz" is taken as a request to
start the named branch at the corresponding remote tracking branch.
+ * "git commit -c/-C/--amend" can be told with a new "--reset-author" option
+ to ignore authorship information in the commit it is taking the message
+ from.
+
* "git describe" can be told to add "-dirty" suffix with "--dirty" option.
* "git diff" learned --submodule option to show a list of one-line logs
instead of differences between the commit object names.
+ * "git diff" learned to honor diff.color.func configuration to paint
+ function name hint printed on the hunk header "@@ -j,k +l,m @@" line
+ in the specified color.
+
+ * "git fetch" learned --all and --multiple options, to run fetch from
+ many repositories, and --prune option to remove remote tracking
+ branches that went stale. These make "git remote update" and "git
+ remote prune" less necessary (there is no plan to remove "remote
+ update" nor "remote prune", though).
+
* "git fsck" by default checks the packfiles (i.e. "--full" is the
default); you can turn it off with "git fsck --no-full".
@@ -88,6 +177,9 @@ Updates since v1.6.5
* "git log --decorate" shows the location of HEAD as well.
+ * "git log" and "git rev-list" learned to take revs and pathspecs from
+ the standard input with the new "--stdin" option.
+
* "--pretty=format" option to "log" family of commands learned:
. to wrap text with the "%w()" specifier.
@@ -105,25 +197,28 @@ Updates since v1.6.5
the shell, which is done by "edit" to give an opportunity to tweak the
contents.
+ * "git send-email" can be told with "--envelope-sender=auto" to use the
+ same address as "From:" address as the envelope sender address.
+
+ * "git send-email" will issue a warning when it defaults to the
+ --chain-reply-to behaviour without being told by the user and
+ instructs to prepare for the change of the default in 1.7.0 release.
+
* In "git submodule add <repository> <path>", <path> is now optional and
inferred from <repository> the same way "git clone <repository>" does.
* "git svn" learned to read SVN 1.5+ and SVK merge tickets.
- * Author names shown in gitweb output are links to search commits by the
- author.
+ * "git svn" learned to recreate empty directories tracked only by SVN.
+ * "gitweb" can optionally render its "blame" output incrementally (this
+ requires JavaScript on the client side).
-(developers)
+ * Author names shown in gitweb output are links to search commits by the
+ author.
Fixes since v1.6.5
------------------
All of the fixes in v1.6.5.X maintenance series are included in this
release, unless otherwise noted.
-
----
-exec >/var/tmp/1
-echo O=$(git describe master)
-O=v1.6.5.3-337-gf341feb
-git shortlog --no-merges $O..master --not maint
diff --git a/Documentation/RelNotes-1.7.0.txt b/Documentation/RelNotes-1.7.0.txt
new file mode 100644
index 0000000..d66a973
--- /dev/null
+++ b/Documentation/RelNotes-1.7.0.txt
@@ -0,0 +1,70 @@
+Git v1.7.0 Release Notes
+========================
+
+Notes on behaviour change
+-------------------------
+
+ * "git push" into a branch that is currently checked out (i.e. pointed by
+ HEAD in a repository that is not bare) is refused by default.
+
+ Similarly, "git push $there :$killed" to delete the branch $killed
+ in a remote repository $there, when $killed branch is the current
+ branch pointed at by its HEAD, will be refused by default.
+
+ Setting the configuration variables receive.denyCurrentBranch and
+ receive.denyDeleteCurrent to 'ignore' in the receiving repository
+ can be used to override these safety features.
+
+ * "git send-email" does not make deep threads by default when sending a
+ patch series with more than two messages. All messages will be sent
+ as a reply to the first message, i.e. cover letter.
+
+ It has been possible to configure send-email to send "shallow thread"
+ by setting sendemail.chainreplyto configuration variable to false. The
+ only thing this release does is to change the default when you haven't
+ configured that variable.
+
+ * "git status" is not "git commit --dry-run" anymore. This change does
+ not affect you if you run the command without pathspec.
+
+ * "git diff" traditionally treated various "ignore whitespace" options
+ only as a way to filter the patch output. "git diff --exit-code -b"
+ exited with non-zero status even if all changes were about changing the
+ ammount of whitespace and nothing else. and "git diff -b" showed the
+ "diff --git" header line for such a change without patch text.
+
+ In this release, the "ignore whitespaces" options affect the semantics
+ of the diff operation. A change that does not affect anything but
+ whitespaces is reported with zero exit status when run with
+ --exit-code, and there is no "diff --git" header for such a change.
+
+
+Updates since v1.6.6
+--------------------
+
+(subsystems)
+
+(portability)
+
+(performance)
+
+(usability, bells and whistles)
+
+ * "git commit --date='<date>'" can be used to override the author date
+ just like "git commit --author='<name> <email>'" can be used to
+ override the author identity.
+
+ * "git status" learned "-s(hort)" output format.
+
+
+Fixes since v1.6.6
+------------------
+
+All of the fixes in v1.6.6.X maintenance series are included in this
+release, unless otherwise noted.
+
+--
+exec >/var/tmp/1
+O=v1.6.6-101-gf012d27
+echo O=$(git describe master)
+git shortlog --no-merges $O..master ^maint
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 76fc84d..c686f86 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -280,6 +280,20 @@ people play with it without having to pick up and apply the patch to
their trees themselves.
------------------------------------------------
+Know the status of your patch after submission
+
+* You can use Git itself to find out when your patch is merged in
+ master. 'git pull --rebase' will automatically skip already-applied
+ patches, and will let you know. This works only if you rebase on top
+ of the branch in which your patch has been merged (i.e. it will not
+ tell you if your patch is merged in pu if you rebase on top of
+ master).
+
+* Read the git mailing list, the maintainer regularly posts messages
+ entitled "What's cooking in git.git" and "What's in git.git" giving
+ the status of various proposed changes.
+
+------------------------------------------------
MUA specific hints
Some of patches I receive or pick up from the list share common
diff --git a/Documentation/config.txt b/Documentation/config.txt
index b77d66d..9f40955 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -297,17 +297,24 @@ false), while all other repositories are assumed to be bare (bare
= true).
core.worktree::
- Set the path to the working tree. The value will not be
- used in combination with repositories found automatically in
- a .git directory (i.e. $GIT_DIR is not set).
+ Set 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. It can be
- a absolute path or relative path to the directory specified by
- --git-dir or GIT_DIR.
- Note: If --git-dir or GIT_DIR are specified but none of
+ an absolute path or a relative path to the .git directory,
+ either specified by --git-dir or GIT_DIR, or automatically
+ discovered.
+ If --git-dir or GIT_DIR are specified but none of
--work-tree, GIT_WORK_TREE and core.worktree is specified,
- the current working directory is regarded as the top directory
- of your working tree.
+ the current working directory is regarded as the root of the
+ work tree.
++
+Note that this variable is honored even when set in a configuration
+file in a ".git" subdirectory of a directory, and its value differs
+from the latter directory (e.g. "/path/to/.git/config" has
+core.worktree set to "/different/path"), which is most likely a
+misconfiguration. Running git commands in "/path/to" directory will
+still use "/different/path" as the root of the work tree and can cause
+great confusion to the users.
core.logAllRefUpdates::
Enable the reflog. Updates to a ref <ref> is logged to the file
@@ -530,7 +537,7 @@ apply.whitespace::
as the '--whitespace' option. See linkgit:git-apply[1].
branch.autosetupmerge::
- Tells 'git-branch' and 'git-checkout' to setup new branches
+ Tells 'git-branch' and 'git-checkout' to set up new branches
so that linkgit:git-pull[1] will appropriately merge from the
starting point branch. Note that even if this option is not set,
this behavior can be chosen per-branch using the `--track`
@@ -635,10 +642,10 @@ color.diff.<slot>::
Use customized color for diff colorization. `<slot>` specifies
which part of the patch to use the specified color, and is one
of `plain` (context text), `meta` (metainformation), `frag`
- (hunk header), `old` (removed lines), `new` (added lines),
- `commit` (commit headers), or `whitespace` (highlighting
- whitespace errors). The values of these variables may be specified as
- in color.branch.<slot>.
+ (hunk header), 'func' (function in hunk header), `old` (removed lines),
+ `new` (added lines), `commit` (commit headers), or `whitespace`
+ (highlighting whitespace errors). The values of these variables may be
+ specified as in color.branch.<slot>.
color.grep::
When set to `always`, always highlight matches. When `false` (or
@@ -718,7 +725,7 @@ diff.autorefreshindex::
contents in the work tree match the contents in the
index. This option defaults to true. Note that this
affects only 'git-diff' Porcelain, and not lower level
- 'diff' commands, such as 'git-diff-files'.
+ 'diff' commands such as 'git-diff-files'.
diff.external::
If this config variable is set, diff generation is not
@@ -834,8 +841,8 @@ format.pretty::
format.thread::
The default threading style for 'git-format-patch'. Can be
- either a boolean value, `shallow` or `deep`. `shallow`
- threading makes every mail a reply to the head of the series,
+ a boolean value, or `shallow` or `deep`. `shallow` threading
+ makes every mail a reply to the head of the series,
where the head is chosen from the cover letter, the
`\--in-reply-to`, and the first patch mail, in this order.
`deep` threading makes every mail a reply to the previous one.
@@ -868,15 +875,12 @@ gc.autopacklimit::
default value is 50. Setting this to 0 disables it.
gc.packrefs::
- 'git-gc' does not run `git pack-refs` in a bare repository by
- default so that older dumb-transport clients can still fetch
- from the repository. Setting this to `true` lets 'git-gc'
- to run `git pack-refs`. Setting this to `false` tells
- 'git-gc' never to run `git pack-refs`. The default setting is
- `notbare`. Enable it only when you know you do not have to
- support such clients. The default setting will change to `true`
- at some stage, and setting this to `false` will continue to
- prevent `git pack-refs` from being run from 'git-gc'.
+ Running `git pack-refs` in a repository renders it
+ unclonable by Git versions prior to 1.5.1.2 over dumb
+ transports such as HTTP. This variable determines whether
+ 'git gc' runs `git pack-refs`. This can be set to "nobare"
+ to enable it within all non-bare repos or it can be set to a
+ boolean value. The default is `true`.
gc.pruneexpire::
When 'git-gc' is run, it will call 'prune --expire 2.weeks.ago'.
@@ -1467,6 +1471,10 @@ remote.<name>.tagopt::
Setting this value to \--no-tags disables automatic tag following when
fetching from remote <name>
+remote.<name>.vcs::
+ Setting this to a value <vcs> will cause git to interact with
+ the remote with the git-remote-<vcs> helper.
+
remotes.<group>::
The list of remotes which are fetched by "git remote update
<group>". See linkgit:git-remote[1].
diff --git a/Documentation/date-formats.txt b/Documentation/date-formats.txt
new file mode 100644
index 0000000..c000f08
--- /dev/null
+++ b/Documentation/date-formats.txt
@@ -0,0 +1,26 @@
+DATE FORMATS
+------------
+
+The GIT_AUTHOR_DATE, GIT_COMMITTER_DATE environment variables
+ifdef::git-commit[]
+and the `--date` option
+endif::git-commit[]
+support the following date formats:
+
+Git internal format::
+ It is `<unix timestamp> <timezone offset>`, where `<unix
+ timestamp>` is the number of seconds since the UNIX epoch.
+ `<timezone offset>` is a positive or negative offset from UTC.
+ For example CET (which is 2 hours ahead UTC) is `+0200`.
+
+RFC 2822::
+ The standard email format as described by RFC 2822, for example
+ `Thu, 07 Apr 2005 22:13:13 +0200`.
+
+ISO 8601::
+ Time and date specified by the ISO 8601 standard, for example
+ `2005-04-07T22:13:13`. The parser accepts a space instead of the
+ `T` character as well.
++
+NOTE: In addition, the date part is accepted in the following formats:
+`YYYY.MM.DD`, `MM/DD/YYYY` and `DD.MM.YYYY`.
diff --git a/Documentation/git-add.txt b/Documentation/git-add.txt
index e93e606..1f1b199 100644
--- a/Documentation/git-add.txt
+++ b/Documentation/git-add.txt
@@ -14,28 +14,32 @@ SYNOPSIS
DESCRIPTION
-----------
-This command adds the current content of new or modified files to the
-index, thus staging that content for inclusion in the next commit.
+This command updates the index using the current content found in
+the working tree, to prepare the content staged for the next commit.
+It typically adds the current content of existing paths as a whole,
+but with some options it can also be used to add content with
+only part of the changes made to the working tree files applied, or
+remove paths that do not exist in the working tree anymore.
The "index" holds a snapshot of the content of the working tree, and it
is this snapshot that is taken as the contents of the next commit. Thus
after making any changes to the working directory, and before running
-the commit command, you must use the 'add' command to add any new or
+the commit command, you must use the `add` command to add any new or
modified files to the index.
This command can be performed multiple times before a commit. It only
adds the content of the specified file(s) at the time the add command is
run; if you want subsequent changes included in the next commit, then
-you must run 'git add' again to add the new content to the index.
+you must run `git add` again to add the new content to the index.
-The 'git status' command can be used to obtain a summary of which
+The `git status` command can be used to obtain a summary of which
files have changes that are staged for the next commit.
-The 'git add' command will not add ignored files by default. If any
-ignored files were explicitly specified on the command line, 'git add'
+The `git add` command will not add ignored files by default. If any
+ignored files were explicitly specified on the command line, `git add`
will fail with a list of ignored files. Ignored files reached by
directory recursion or filename globbing performed by Git (quote your
-globs before the shell) will be silently ignored. The 'add' command can
+globs before the shell) will be silently ignored. The `add` command can
be used to add ignored files with the `-f` (force) option.
Please see linkgit:git-commit[1] for alternative ways to add content to a
@@ -92,28 +96,31 @@ apply.
-u::
--update::
- Update only files that git already knows about, staging modified
- content for commit and marking deleted files for removal. This
- is similar
- to what "git commit -a" does in preparation for making a commit,
- except that the update is limited to paths specified on the
- command line. If no paths are specified, all tracked files in the
- current directory and its subdirectories are updated.
+ Only match <filepattern> against already tracked files in
+ the index rather than the working tree. That means that it
+ will never stage new files, but that it will stage modified
+ new contents of tracked files and that it will remove files
+ from the index if the corresponding files in the working tree
+ have been removed.
++
+If no <filepattern> is given, default to "."; in other words,
+update all tracked files in the current directory and its
+subdirectories.
-A::
--all::
- Update files that git already knows about (same as '\--update')
- and add all untracked files that are not ignored by '.gitignore'
- mechanism.
-
+ Like `-u`, but match <filepattern> against files in the
+ working tree in addition to the index. That means that it
+ will find new files as well as staging modified content and
+ removing files that are no longer in the working tree.
-N::
--intent-to-add::
Record only the fact that the path will be added later. An entry
for the path is placed in the index with no content. This is
useful for, among other things, showing the unstaged content of
- such files with 'git diff' and committing them with 'git commit
- -a'.
+ such files with `git diff` and committing them with `git commit
+ -a`.
--refresh::
Don't add the file(s), but only refresh their stat()
@@ -133,7 +140,7 @@ apply.
Configuration
-------------
-The optional configuration variable 'core.excludesfile' indicates a path to a
+The optional configuration variable `core.excludesfile` indicates a path to a
file containing patterns of file names to exclude from git-add, similar to
$GIT_DIR/info/exclude. Patterns in the exclude file are used in addition to
those in info/exclude. See linkgit:gitrepository-layout[5].
@@ -181,7 +188,7 @@ and type return, like this:
What now> 1
------------
-You also could say "s" or "sta" or "status" above as long as the
+You also could say `s` or `sta` or `status` above as long as the
choice is unique.
The main command loop has 6 subcommands (plus help and quit).
@@ -189,9 +196,9 @@ The main command loop has 6 subcommands (plus help and quit).
status::
This shows the change between HEAD and index (i.e. what will be
- committed if you say "git commit"), and between index and
+ committed if you say `git commit`), and between index and
working tree files (i.e. what you could stage further before
- "git commit" using "git-add") for each path. A sample output
+ `git commit` using `git add`) for each path. A sample output
looks like this:
+
------------
diff --git a/Documentation/git-archive.txt b/Documentation/git-archive.txt
index 3d1c1e7..e579791 100644
--- a/Documentation/git-archive.txt
+++ b/Documentation/git-archive.txt
@@ -74,8 +74,9 @@ OPTIONS
The tree or commit to produce an archive for.
path::
- If one or more paths are specified, include only these in the
- archive, otherwise include all files and subdirectories.
+ Without an optional path parameter, all files and subdirectories
+ of the current working directory are included in the archive.
+ If one or more paths are specified, only these are included.
BACKEND EXTRA OPTIONS
---------------------
diff --git a/Documentation/git-bisect-lk2009.txt b/Documentation/git-bisect-lk2009.txt
new file mode 100644
index 0000000..6b7b2e5
--- /dev/null
+++ b/Documentation/git-bisect-lk2009.txt
@@ -0,0 +1,1358 @@
+Fighting regressions with git bisect
+====================================
+:Author: Christian Couder
+:Email: chriscool@tuxfamily.org
+:Date: 2009/11/08
+
+Abstract
+--------
+
+"git bisect" enables software users and developers to easily find the
+commit that introduced a regression. We show why it is important to
+have good tools to fight regressions. We describe how "git bisect"
+works from the outside and the algorithms it uses inside. Then we
+explain how to take advantage of "git bisect" to improve current
+practices. And we discuss how "git bisect" could improve in the
+future.
+
+
+Introduction to "git bisect"
+----------------------------
+
+Git is a Distributed Version Control system (DVCS) created by Linus
+Torvalds and maintained by Junio Hamano.
+
+In Git like in many other Version Control Systems (VCS), the different
+states of the data that is managed by the system are called
+commits. And, as VCS are mostly used to manage software source code,
+sometimes "interesting" changes of behavior in the software are
+introduced in some commits.
+
+In fact people are specially interested in commits that introduce a
+"bad" behavior, called a bug or a regression. They are interested in
+these commits because a commit (hopefully) contains a very small set
+of source code changes. And it's much easier to understand and
+properly fix a problem when you only need to check a very small set of
+changes, than when you don't know where look in the first place.
+
+So to help people find commits that introduce a "bad" behavior, the
+"git bisect" set of commands was invented. And it follows of course
+that in "git bisect" parlance, commits where the "interesting
+behavior" is present are called "bad" commits, while other commits are
+called "good" commits. And a commit that introduce the behavior we are
+interested in is called a "first bad commit". Note that there could be
+more than one "first bad commit" in the commit space we are searching.
+
+So "git bisect" is designed to help find a "first bad commit". And to
+be as efficient as possible, it tries to perform a binary search.
+
+
+Fighting regressions overview
+-----------------------------
+
+Regressions: a big problem
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Regressions are a big problem in the software industry. But it's
+difficult to put some real numbers behind that claim.
+
+There are some numbers about bugs in general, like a NIST study in
+2002 <<1>> that said:
+
+_____________
+Software bugs, or errors, are so prevalent and so detrimental that
+they cost the U.S. economy an estimated $59.5 billion annually, or
+about 0.6 percent of the gross domestic product, according to a newly
+released study commissioned by the Department of Commerce's National
+Institute of Standards and Technology (NIST). At the national level,
+over half of the costs are borne by software users and the remainder
+by software developers/vendors. The study also found that, although
+all errors cannot be removed, more than a third of these costs, or an
+estimated $22.2 billion, could be eliminated by an improved testing
+infrastructure that enables earlier and more effective identification
+and removal of software defects. These are the savings associated with
+finding an increased percentage (but not 100 percent) of errors closer
+to the development stages in which they are introduced. Currently,
+over half of all errors are not found until "downstream" in the
+development process or during post-sale software use.
+_____________
+
+And then:
+
+_____________
+Software developers already spend approximately 80 percent of
+development costs on identifying and correcting defects, and yet few
+products of any type other than software are shipped with such high
+levels of errors.
+_____________
+
+Eventually the conclusion started with:
+
+_____________
+The path to higher software quality is significantly improved software
+testing.
+_____________
+
+There are other estimates saying that 80% of the cost related to
+software is about maintenance <<2>>.
+
+Though, according to Wikipedia <<3>>:
+
+_____________
+A common perception of maintenance is that it is merely fixing
+bugs. However, studies and surveys over the years have indicated that
+the majority, over 80%, of the maintenance effort is used for
+non-corrective actions (Pigosky 1997). This perception is perpetuated
+by users submitting problem reports that in reality are functionality
+enhancements to the system.
+_____________
+
+But we can guess that improving on existing software is very costly
+because you have to watch out for regressions. At least this would
+make the above studies consistent among themselves.
+
+Of course some kind of software is developed, then used during some
+time without being improved on much, and then finally thrown away. In
+this case, of course, regressions may not be a big problem. But on the
+other hand, there is a lot of big software that is continually
+developed and maintained during years or even tens of years by a lot
+of people. And as there are often many people who depend (sometimes
+critically) on such software, regressions are a really big problem.
+
+One such software is the linux kernel. And if we look at the linux
+kernel, we can see that a lot of time and effort is spent to fight
+regressions. The release cycle start with a 2 weeks long merge
+window. Then the first release candidate (rc) version is tagged. And
+after that about 7 or 8 more rc versions will appear with around one
+week between each of them, before the final release.
+
+The time between the first rc release and the final release is
+supposed to be used to test rc versions and fight bugs and especially
+regressions. And this time is more than 80% of the release cycle
+time. But this is not the end of the fight yet, as of course it
+continues after the release.
+
+And then this is what Ingo Molnar (a well known linux kernel
+developer) says about his use of git bisect:
+
+_____________
+I most actively use it during the merge window (when a lot of trees
+get merged upstream and when the influx of bugs is the highest) - and
+yes, there have been cases that i used it multiple times a day. My
+average is roughly once a day.
+_____________
+
+So regressions are fought all the time by developers, and indeed it is
+well known that bugs should be fixed as soon as possible, so as soon
+as they are found. That's why it is interesting to have good tools for
+this purpose.
+
+Other tools to fight regressions
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+So what are the tools used to fight regressions? They are nearly the
+same as those used to fight regular bugs. The only specific tools are
+test suites and tools similar as "git bisect".
+
+Test suites are very nice. But when they are used alone, they are
+supposed to be used so that all the tests are checked after each
+commit. This means that they are not very efficient, because many
+tests are run for no interesting result, and they suffer from
+combinational explosion.
+
+In fact the problem is that big software often has many different
+configuration options and that each test case should pass for each
+configuration after each commit. So if you have for each release: N
+configurations, M commits and T test cases, you should perform:
+
+-------------
+N * M * T tests
+-------------
+
+where N, M and T are all growing with the size your software.
+
+So very soon it will not be possible to completely test everything.
+
+And if some bugs slip through your test suite, then you can add a test
+to your test suite. But if you want to use your new improved test
+suite to find where the bug slipped in, then you will either have to
+emulate a bisection process or you will perhaps bluntly test each
+commit backward starting from the "bad" commit you have which may be
+very wasteful.
+
+"git bisect" overview
+---------------------
+
+Starting a bisection
+~~~~~~~~~~~~~~~~~~~~
+
+The first "git bisect" subcommand to use is "git bisect start" to
+start the search. Then bounds must be set to limit the commit
+space. This is done usually by giving one "bad" and at least one
+"good" commit. They can be passed in the initial call to "git bisect
+start" like this:
+
+-------------
+$ git bisect start [BAD [GOOD...]]
+-------------
+
+or they can be set using:
+
+-------------
+$ git bisect bad [COMMIT]
+-------------
+
+and:
+
+-------------
+$ git bisect good [COMMIT...]
+-------------
+
+where BAD, GOOD and COMMIT are all names that can be resolved to a
+commit.
+
+Then "git bisect" will checkout a commit of its choosing and ask the
+user to test it, like this:
+
+-------------
+$ git bisect start v2.6.27 v2.6.25
+Bisecting: 10928 revisions left to test after this (roughly 14 steps)
+[2ec65f8b89ea003c27ff7723525a2ee335a2b393] x86: clean up using max_low_pfn on 32-bit
+-------------
+
+Note that the example that we will use is really a toy example, we
+will be looking for the first commit that has a version like
+"2.6.26-something", that is the commit that has a "SUBLEVEL = 26" line
+in the top level Makefile. This is a toy example because there are
+better ways to find this commit with git than using "git bisect" (for
+example "git blame" or "git log -S<string>").
+
+Driving a bisection manually
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+At this point there are basically 2 ways to drive the search. It can
+be driven manually by the user or it can be driven automatically by a
+script or a command.
+
+If the user is driving it, then at each step of the search, the user
+will have to test the current commit and say if it is "good" or "bad"
+using the "git bisect good" or "git bisect bad" commands respectively
+that have been described above. For example:
+
+-------------
+$ git bisect bad
+Bisecting: 5480 revisions left to test after this (roughly 13 steps)
+[66c0b394f08fd89236515c1c84485ea712a157be] KVM: kill file->f_count abuse in kvm
+-------------
+
+And after a few more steps like that, "git bisect" will eventually
+find a first bad commit:
+
+-------------
+$ git bisect bad
+2ddcca36c8bcfa251724fe342c8327451988be0d is the first bad commit
+commit 2ddcca36c8bcfa251724fe342c8327451988be0d
+Author: Linus Torvalds <torvalds@linux-foundation.org>
+Date: Sat May 3 11:59:44 2008 -0700
+
+ Linux 2.6.26-rc1
+
+:100644 100644 5cf8258195331a4dbdddff08b8d68642638eea57 4492984efc09ab72ff6219a7bc21fb6a957c4cd5 M Makefile
+-------------
+
+At this point we can see what the commit does, check it out (if it's
+not already checked out) or tinker with it, for example:
+
+-------------
+$ git show HEAD
+commit 2ddcca36c8bcfa251724fe342c8327451988be0d
+Author: Linus Torvalds <torvalds@linux-foundation.org>
+Date: Sat May 3 11:59:44 2008 -0700
+
+ Linux 2.6.26-rc1
+
+diff --git a/Makefile b/Makefile
+index 5cf8258..4492984 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ VERSION = 2
+ PATCHLEVEL = 6
+-SUBLEVEL = 25
+-EXTRAVERSION =
++SUBLEVEL = 26
++EXTRAVERSION = -rc1
+ NAME = Funky Weasel is Jiggy wit it
+
+ # *DOCUMENTATION*
+-------------
+
+And when we are finished we can use "git bisect reset" to go back to
+the branch we were in before we started bisecting:
+
+-------------
+$ git bisect reset
+Checking out files: 100% (21549/21549), done.
+Previous HEAD position was 2ddcca3... Linux 2.6.26-rc1
+Switched to branch 'master'
+-------------
+
+Driving a bisection automatically
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The other way to drive the bisection process is to tell "git bisect"
+to launch a script or command at each bisection step to know if the
+current commit is "good" or "bad". To do that, we use the "git bisect
+run" command. For example:
+
+-------------
+$ git bisect start v2.6.27 v2.6.25
+Bisecting: 10928 revisions left to test after this (roughly 14 steps)
+[2ec65f8b89ea003c27ff7723525a2ee335a2b393] x86: clean up using max_low_pfn on 32-bit
+$
+$ git bisect run grep '^SUBLEVEL = 25' Makefile
+running grep ^SUBLEVEL = 25 Makefile
+Bisecting: 5480 revisions left to test after this (roughly 13 steps)
+[66c0b394f08fd89236515c1c84485ea712a157be] KVM: kill file->f_count abuse in kvm
+running grep ^SUBLEVEL = 25 Makefile
+SUBLEVEL = 25
+Bisecting: 2740 revisions left to test after this (roughly 12 steps)
+[671294719628f1671faefd4882764886f8ad08cb] V4L/DVB(7879): Adding cx18 Support for mxl5005s
+...
+...
+running grep ^SUBLEVEL = 25 Makefile
+Bisecting: 0 revisions left to test after this (roughly 0 steps)
+[2ddcca36c8bcfa251724fe342c8327451988be0d] Linux 2.6.26-rc1
+running grep ^SUBLEVEL = 25 Makefile
+2ddcca36c8bcfa251724fe342c8327451988be0d is the first bad commit
+commit 2ddcca36c8bcfa251724fe342c8327451988be0d
+Author: Linus Torvalds <torvalds@linux-foundation.org>
+Date: Sat May 3 11:59:44 2008 -0700
+
+ Linux 2.6.26-rc1
+
+:100644 100644 5cf8258195331a4dbdddff08b8d68642638eea57 4492984efc09ab72ff6219a7bc21fb6a957c4cd5 M Makefile
+bisect run success
+-------------
+
+In this example, we passed "grep '^SUBLEVEL = 25' Makefile" as
+parameter to "git bisect run". This means that at each step, the grep
+command we passed will be launched. And if it exits with code 0 (that
+means success) then git bisect will mark the current state as
+"good". If it exits with code 1 (or any code between 1 and 127
+included, except the special code 125), then the current state will be
+marked as "bad".
+
+Exit code between 128 and 255 are special to "git bisect run". They
+make it stop immediately the bisection process. This is useful for
+example if the command passed takes too long to complete, because you
+can kill it with a signal and it will stop the bisection process.
+
+It can also be useful in scripts passed to "git bisect run" to "exit
+255" if some very abnormal situation is detected.
+
+Avoiding untestable commits
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Sometimes it happens that the current state cannot be tested, for
+example if it does not compile because there was a bug preventing it
+at that time. This is what the special exit code 125 is for. It tells
+"git bisect run" that the current commit should be marked as
+untestable and that another one should be chosen and checked out.
+
+If the bisection process is driven manually, you can use "git bisect
+skip" to do the same thing. (In fact the special exit code 125 makes
+"git bisect run" use "git bisect skip" in the background.)
+
+Or if you want more control, you can inspect the current state using
+for example "git bisect visualize". It will launch gitk (or "git log"
+if the DISPLAY environment variable is not set) to help you find a
+better bisection point.
+
+Either way, if you have a string of untestable commits, it might
+happen that the regression you are looking for has been introduced by
+one of these untestable commits. In this case it's not possible to
+tell for sure which commit introduced the regression.
+
+So if you used "git bisect skip" (or the run script exited with
+special code 125) you could get a result like this:
+
+-------------
+There are only 'skip'ped commits left to test.
+The first bad commit could be any of:
+15722f2fa328eaba97022898a305ffc8172db6b1
+78e86cf3e850bd755bb71831f42e200626fbd1e0
+e15b73ad3db9b48d7d1ade32f8cd23a751fe0ace
+070eab2303024706f2924822bfec8b9847e4ac1b
+We cannot bisect more!
+-------------
+
+Saving a log and replaying it
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+If you want to show other people your bisection process, you can get a
+log using for example:
+
+-------------
+$ git bisect log > bisect_log.txt
+-------------
+
+And it is possible to replay it using:
+
+-------------
+$ git bisect replay bisect_log.txt
+-------------
+
+
+"git bisect" details
+--------------------
+
+Bisection algorithm
+~~~~~~~~~~~~~~~~~~~
+
+As the Git commits form a directed acyclic graph (DAG), finding the
+best bisection commit to test at each step is not so simple. Anyway
+Linus found and implemented a "truly stupid" algorithm, later improved
+by Junio Hamano, that works quite well.
+
+So the algorithm used by "git bisect" to find the best bisection
+commit when there are no skipped commits is the following:
+
+1) keep only the commits that:
+
+a) are ancestor of the "bad" commit (including the "bad" commit itself),
+b) are not ancestor of a "good" commit (excluding the "good" commits).
+
+This means that we get rid of the uninteresting commits in the DAG.
+
+For example if we start with a graph like this:
+
+-------------
+G-Y-G-W-W-W-X-X-X-X
+ \ /
+ W-W-B
+ /
+Y---G-W---W
+ \ / \
+Y-Y X-X-X-X
+
+-> time goes this way ->
+-------------
+
+where B is the "bad" commit, "G" are "good" commits and W, X, and Y
+are other commits, we will get the following graph after this first
+step:
+
+-------------
+W-W-W
+ \
+ W-W-B
+ /
+W---W
+-------------
+
+So only the W and B commits will be kept. Because commits X and Y will
+have been removed by rules a) and b) respectively, and because commits
+G are removed by rule b) too.
+
+Note for git users, that it is equivalent as keeping only the commit
+given by:
+
+-------------
+git rev-list BAD --not GOOD1 GOOD2...
+-------------
+
+Also note that we don't require the commits that are kept to be
+descendants of a "good" commit. So in the following example, commits W
+and Z will be kept:
+
+-------------
+G-W-W-W-B
+ /
+Z-Z
+-------------
+
+2) starting from the "good" ends of the graph, associate to each
+commit the number of ancestors it has plus one
+
+For example with the following graph where H is the "bad" commit and A
+and D are some parents of some "good" commits:
+
+-------------
+A-B-C
+ \
+ F-G-H
+ /
+D---E
+-------------
+
+this will give:
+
+-------------
+1 2 3
+A-B-C
+ \6 7 8
+ F-G-H
+1 2/
+D---E
+-------------
+
+3) associate to each commit: min(X, N - X)
+
+where X is the value associated to the commit in step 2) and N is the
+total number of commits in the graph.
+
+In the above example we have N = 8, so this will give:
+
+-------------
+1 2 3
+A-B-C
+ \2 1 0
+ F-G-H
+1 2/
+D---E
+-------------
+
+4) the best bisection point is the commit with the highest associated
+number
+
+So in the above example the best bisection point is commit C.
+
+5) note that some shortcuts are implemented to speed up the algorithm
+
+As we know N from the beginning, we know that min(X, N - X) can't be
+greater than N/2. So during steps 2) and 3), if we would associate N/2
+to a commit, then we know this is the best bisection point. So in this
+case we can just stop processing any other commit and return the
+current commit.
+
+Bisection algorithm debugging
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+For any commit graph, you can see the number associated with each
+commit using "git rev-list --bisect-all".
+
+For example, for the above graph, a command like:
+
+-------------
+$ git rev-list --bisect-all BAD --not GOOD1 GOOD2
+-------------
+
+would output something like:
+
+-------------
+e15b73ad3db9b48d7d1ade32f8cd23a751fe0ace (dist=3)
+15722f2fa328eaba97022898a305ffc8172db6b1 (dist=2)
+78e86cf3e850bd755bb71831f42e200626fbd1e0 (dist=2)
+a1939d9a142de972094af4dde9a544e577ddef0e (dist=2)
+070eab2303024706f2924822bfec8b9847e4ac1b (dist=1)
+a3864d4f32a3bf5ed177ddef598490a08760b70d (dist=1)
+a41baa717dd74f1180abf55e9341bc7a0bb9d556 (dist=1)
+9e622a6dad403b71c40979743bb9d5be17b16bd6 (dist=0)
+-------------
+
+Bisection algorithm discussed
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+First let's define "best bisection point". We will say that a commit X
+is a best bisection point or a best bisection commit if knowing its
+state ("good" or "bad") gives as much information as possible whether
+the state of the commit happens to be "good" or "bad".
+
+This means that the best bisection commits are the commits where the
+following function is maximum:
+
+-------------
+f(X) = min(information_if_good(X), information_if_bad(X))
+-------------
+
+where information_if_good(X) is the information we get if X is good
+and information_if_bad(X) is the information we get if X is bad.
+
+Now we will suppose that there is only one "first bad commit". This
+means that all its descendants are "bad" and all the other commits are
+"good". And we will suppose that all commits have an equal probability
+of being good or bad, or of being the first bad commit, so knowing the
+state of c commits gives always the same amount of information
+wherever these c commits are on the graph and whatever c is. (So we
+suppose that these commits being for example on a branch or near a
+good or a bad commit does not give more or less information).
+
+Let's also suppose that we have a cleaned up graph like one after step
+1) in the bisection algorithm above. This means that we can measure
+the information we get in terms of number of commit we can remove from
+the graph..
+
+And let's take a commit X in the graph.
+
+If X is found to be "good", then we know that its ancestors are all
+"good", so we want to say that:
+
+-------------
+information_if_good(X) = number_of_ancestors(X) (TRUE)
+-------------
+
+And this is true because at step 1) b) we remove the ancestors of the
+"good" commits.
+
+If X is found to be "bad", then we know that its descendants are all
+"bad", so we want to say that:
+
+-------------
+information_if_bad(X) = number_of_descendants(X) (WRONG)
+-------------
+
+But this is wrong because at step 1) a) we keep only the ancestors of
+the bad commit. So we get more information when a commit is marked as
+"bad", because we also know that the ancestors of the previous "bad"
+commit that are not ancestors of the new "bad" commit are not the
+first bad commit. We don't know if they are good or bad, but we know
+that they are not the first bad commit because they are not ancestor
+of the new "bad" commit.
+
+So when a commit is marked as "bad" we know we can remove all the
+commits in the graph except those that are ancestors of the new "bad"
+commit. This means that:
+
+-------------
+information_if_bad(X) = N - number_of_ancestors(X) (TRUE)
+-------------
+
+where N is the number of commits in the (cleaned up) graph.
+
+So in the end this means that to find the best bisection commits we
+should maximize the function:
+
+-------------
+f(X) = min(number_of_ancestors(X), N - number_of_ancestors(X))
+-------------
+
+And this is nice because at step 2) we compute number_of_ancestors(X)
+and so at step 3) we compute f(X).
+
+Let's take the following graph as an example:
+
+-------------
+ G-H-I-J
+ / \
+A-B-C-D-E-F O
+ \ /
+ K-L-M-N
+-------------
+
+If we compute the following non optimal function on it:
+
+-------------
+g(X) = min(number_of_ancestors(X), number_of_descendants(X))
+-------------
+
+we get:
+
+-------------
+ 4 3 2 1
+ G-H-I-J
+1 2 3 4 5 6/ \0
+A-B-C-D-E-F O
+ \ /
+ K-L-M-N
+ 4 3 2 1
+-------------
+
+but with the algorithm used by git bisect we get:
+
+-------------
+ 7 7 6 5
+ G-H-I-J
+1 2 3 4 5 6/ \0
+A-B-C-D-E-F O
+ \ /
+ K-L-M-N
+ 7 7 6 5
+-------------
+
+So we chose G, H, K or L as the best bisection point, which is better
+than F. Because if for example L is bad, then we will know not only
+that L, M and N are bad but also that G, H, I and J are not the first
+bad commit (since we suppose that there is only one first bad commit
+and it must be an ancestor of L).
+
+So the current algorithm seems to be the best possible given what we
+initially supposed.
+
+Skip algorithm
+~~~~~~~~~~~~~~
+
+When some commits have been skipped (using "git bisect skip"), then
+the bisection algorithm is the same for step 1) to 3). But then we use
+roughly the following steps:
+
+6) sort the commit by decreasing associated value
+
+7) if the first commit has not been skipped, we can return it and stop
+here
+
+8) otherwise filter out all the skipped commits in the sorted list
+
+9) use a pseudo random number generator (PRNG) to generate a random
+number between 0 and 1
+
+10) multiply this random number with its square root to bias it toward
+0
+
+11) multiply the result by the number of commits in the filtered list
+to get an index into this list
+
+12) return the commit at the computed index
+
+Skip algorithm discussed
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+After step 7) (in the skip algorithm), we could check if the second
+commit has been skipped and return it if it is not the case. And in
+fact that was the algorithm we used from when "git bisect skip" was
+developed in git version 1.5.4 (released on February 1st 2008) until
+git version 1.6.4 (released July 29th 2009).
+
+But Ingo Molnar and H. Peter Anvin (another well known linux kernel
+developer) both complained that sometimes the best bisection points
+all happened to be in an area where all the commits are
+untestable. And in this case the user was asked to test many
+untestable commits, which could be very inefficient.
+
+Indeed untestable commits are often untestable because a breakage was
+introduced at one time, and that breakage was fixed only after many
+other commits were introduced.
+
+This breakage is of course most of the time unrelated to the breakage
+we are trying to locate in the commit graph. But it prevents us to
+know if the interesting "bad behavior" is present or not.
+
+So it is a fact that commits near an untestable commit have a high
+probability of being untestable themselves. And the best bisection
+commits are often found together too (due to the bisection algorithm).
+
+This is why it is a bad idea to just chose the next best unskipped
+bisection commit when the first one has been skipped.
+
+We found that most commits on the graph may give quite a lot of
+information when they are tested. And the commits that will not on
+average give a lot of information are the one near the good and bad
+commits.
+
+So using a PRNG with a bias to favor commits away from the good and
+bad commits looked like a good choice.
+
+One obvious improvement to this algorithm would be to look for a
+commit that has an associated value near the one of the best bisection
+commit, and that is on another branch, before using the PRNG. Because
+if such a commit exists, then it is not very likely to be untestable
+too, so it will probably give more information than a nearly randomly
+chosen one.
+
+Checking merge bases
+~~~~~~~~~~~~~~~~~~~~
+
+There is another tweak in the bisection algorithm that has not been
+described in the "bisection algorithm" above.
+
+We supposed in the previous examples that the "good" commits were
+ancestors of the "bad" commit. But this is not a requirement of "git
+bisect".
+
+Of course the "bad" commit cannot be an ancestor of a "good" commit,
+because the ancestors of the good commits are supposed to be
+"good". And all the "good" commits must be related to the bad commit.
+They cannot be on a branch that has no link with the branch of the
+"bad" commit. But it is possible for a good commit to be related to a
+bad commit and yet not be neither one of its ancestor nor one of its
+descendants.
+
+For example, there can be a "main" branch, and a "dev" branch that was
+forked of the main branch at a commit named "D" like this:
+
+-------------
+A-B-C-D-E-F-G <--main
+ \
+ H-I-J <--dev
+-------------
+
+The commit "D" is called a "merge base" for branch "main" and "dev"
+because it's the best common ancestor for these branches for a merge.
+
+Now let's suppose that commit J is bad and commit G is good and that
+we apply the bisection algorithm like it has been previously
+described.
+
+As described in step 1) b) of the bisection algorithm, we remove all
+the ancestors of the good commits because they are supposed to be good
+too.
+
+So we would be left with only:
+
+-------------
+H-I-J
+-------------
+
+But what happens if the first bad commit is "B" and if it has been
+fixed in the "main" branch by commit "F"?
+
+The result of such a bisection would be that we would find that H is
+the first bad commit, when in fact it's B. So that would be wrong!
+
+And yes it's can happen in practice that people working on one branch
+are not aware that people working on another branch fixed a bug! It
+could also happen that F fixed more than one bug or that it is a
+revert of some big development effort that was not ready to be
+released.
+
+In fact development teams often maintain both a development branch and
+a maintenance branch, and it would be quite easy for them if "git
+bisect" just worked when they want to bisect a regression on the
+development branch that is not on the maintenance branch. They should
+be able to start bisecting using:
+
+-------------
+$ git bisect start dev main
+-------------
+
+To enable that additional nice feature, when a bisection is started
+and when some good commits are not ancestors of the bad commit, we
+first compute the merge bases between the bad and the good commits and
+we chose these merge bases as the first commits that will be checked
+out and tested.
+
+If it happens that one merge base is bad, then the bisection process
+is stopped with a message like:
+
+-------------
+The merge base BBBBBB is bad.
+This means the bug has been fixed between BBBBBB and [GGGGGG,...].
+-------------
+
+where BBBBBB is the sha1 hash of the bad merge base and [GGGGGG,...]
+is a comma separated list of the sha1 of the good commits.
+
+If some of the merge bases are skipped, then the bisection process
+continues, but the following message is printed for each skipped merge
+base:
+
+-------------
+Warning: the merge base between BBBBBB and [GGGGGG,...] must be skipped.
+So we cannot be sure the first bad commit is between MMMMMM and BBBBBB.
+We continue anyway.
+-------------
+
+where BBBBBB is the sha1 hash of the bad commit, MMMMMM is the sha1
+hash of the merge base that is skipped and [GGGGGG,...] is a comma
+separated list of the sha1 of the good commits.
+
+So if there is no bad merge base, the bisection process continues as
+usual after this step.
+
+Best bisecting practices
+------------------------
+
+Using test suites and git bisect together
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+If you both have a test suite and use git bisect, then it becomes less
+important to check that all tests pass after each commit. Though of
+course it is probably a good idea to have some checks to avoid
+breaking too many things because it could make bisecting other bugs
+more difficult.
+
+You can focus your efforts to check at a few points (for example rc
+and beta releases) that all the T test cases pass for all the N
+configurations. And when some tests don't pass you can use "git
+bisect" (or better "git bisect run"). So you should perform roughly:
+
+-------------
+c * N * T + b * M * log2(M) tests
+-------------
+
+where c is the number of rounds of test (so a small constant) and b is
+the ratio of bug per commit (hopefully a small constant too).
+
+So of course it's much better as it's O(N \* T) vs O(N \* T \* M) if
+you would test everything after each commit.
+
+This means that test suites are good to prevent some bugs from being
+committed and they are also quite good to tell you that you have some
+bugs. But they are not so good to tell you where some bugs have been
+introduced. To tell you that efficiently, git bisect is needed.
+
+The other nice thing with test suites, is that when you have one, you
+already know how to test for bad behavior. So you can use this
+knowledge to create a new test case for "git bisect" when it appears
+that there is a regression. So it will be easier to bisect the bug and
+fix it. And then you can add the test case you just created to your
+test suite.
+
+So if you know how to create test cases and how to bisect, you will be
+subject to a virtuous circle:
+
+more tests => easier to create tests => easier to bisect => more tests
+
+So test suites and "git bisect" are complementary tools that are very
+powerful and efficient when used together.
+
+Bisecting build failures
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+You can very easily automatically bisect broken builds using something
+like:
+
+-------------
+$ git bisect start BAD GOOD
+$ git bisect run make
+-------------
+
+Passing sh -c "some commands" to "git bisect run"
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+For example:
+
+-------------
+$ git bisect run sh -c "make || exit 125; ./my_app | grep 'good output'"
+-------------
+
+On the other hand if you do this often, then it can be worth having
+scripts to avoid too much typing.
+
+Finding performance regressions
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Here is an example script that comes slightly modified from a real
+world script used by Junio Hamano <<4>>.
+
+This script can be passed to "git bisect run" to find the commit that
+introduced a performance regression:
+
+-------------
+#!/bin/sh
+
+# Build errors are not what I am interested in.
+make my_app || exit 255
+
+# We are checking if it stops in a reasonable amount of time, so
+# let it run in the background...
+
+./my_app >log 2>&1 &
+
+# ... and grab its process ID.
+pid=$!
+
+# ... and then wait for sufficiently long.
+sleep $NORMAL_TIME
+
+# ... and then see if the process is still there.
+if kill -0 $pid
+then
+ # It is still running -- that is bad.
+ kill $pid; sleep 1; kill $pid;
+ exit 1
+else
+ # It has already finished (the $pid process was no more),
+ # and we are happy.
+ exit 0
+fi
+-------------
+
+Following general best practices
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+It is obviously a good idea not to have commits with changes that
+knowingly break things, even if some other commits later fix the
+breakage.
+
+It is also a good idea when using any VCS to have only one small
+logical change in each commit.
+
+The smaller the changes in your commit, the most effective "git
+bisect" will be. And you will probably need "git bisect" less in the
+first place, as small changes are easier to review even if they are
+only reviewed by the commiter.
+
+Another good idea is to have good commit messages. They can be very
+helpful to understand why some changes were made.
+
+These general best practices are very helpful if you bisect often.
+
+Avoiding bug prone merges
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+First merges by themselves can introduce some regressions even when
+the merge needs no source code conflict resolution. This is because a
+semantic change can happen in one branch while the other branch is not
+aware of it.
+
+For example one branch can change the semantic of a function while the
+other branch add more calls to the same function.
+
+This is made much worse if many files have to be fixed to resolve
+conflicts. That's why such merges are called "evil merges". They can
+make regressions very difficult to track down. It can even be
+misleading to know the first bad commit if it happens to be such a
+merge, because people might think that the bug comes from bad conflict
+resolution when it comes from a semantic change in one branch.
+
+Anyway "git rebase" can be used to linearize history. This can be used
+either to avoid merging in the first place. Or it can be used to
+bisect on a linear history instead of the non linear one, as this
+should give more information in case of a semantic change in one
+branch.
+
+Merges can be also made simpler by using smaller branches or by using
+many topic branches instead of only long version related branches.
+
+And testing can be done more often in special integration branches
+like linux-next for the linux kernel.
+
+Adapting your work-flow
+~~~~~~~~~~~~~~~~~~~~~~~
+
+A special work-flow to process regressions can give great results.
+
+Here is an example of a work-flow used by Andreas Ericsson:
+
+* write, in the test suite, a test script that exposes the regression
+* use "git bisect run" to find the commit that introduced it
+* fix the bug that is often made obvious by the previous step
+* commit both the fix and the test script (and if needed more tests)
+
+And here is what Andreas said about this work-flow <<5>>:
+
+_____________
+To give some hard figures, we used to have an average report-to-fix
+cycle of 142.6 hours (according to our somewhat weird bug-tracker
+which just measures wall-clock time). Since we moved to git, we've
+lowered that to 16.2 hours. Primarily because we can stay on top of
+the bug fixing now, and because everyone's jockeying to get to fix
+bugs (we're quite proud of how lazy we are to let git find the bugs
+for us). Each new release results in ~40% fewer bugs (almost certainly
+due to how we now feel about writing tests).
+_____________
+
+Clearly this work-flow uses the virtuous circle between test suites
+and "git bisect". In fact it makes it the standard procedure to deal
+with regression.
+
+In other messages Andreas says that they also use the "best practices"
+described above: small logical commits, topic branches, no evil
+merge,... These practices all improve the bisectability of the commit
+graph, by making it easier and more useful to bisect.
+
+So a good work-flow should be designed around the above points. That
+is making bisecting easier, more useful and standard.
+
+Involving QA people and if possible end users
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+One nice about "git bisect" is that it is not only a developer
+tool. It can effectively be used by QA people or even end users (if
+they have access to the source code or if they can get access to all
+the builds).
+
+There was a discussion at one point on the linux kernel mailing list
+of whether it was ok to always ask end user to bisect, and very good
+points were made to support the point of view that it is ok.
+
+For example David Miller wrote <<6>>:
+
+_____________
+What people don't get is that this is a situation where the "end node
+principle" applies. When you have limited resources (here: developers)
+you don't push the bulk of the burden upon them. Instead you push
+things out to the resource you have a lot of, the end nodes (here:
+users), so that the situation actually scales.
+_____________
+
+This means that it is often "cheaper" if QA people or end users can do
+it.
+
+What is interesting too is that end users that are reporting bugs (or
+QA people that reproduced a bug) have access to the environment where
+the bug happens. So they can often more easily reproduce a
+regression. And if they can bisect, then more information will be
+extracted from the environment where the bug happens, which means that
+it will be easier to understand and then fix the bug.
+
+For open source projects it can be a good way to get more useful
+contributions from end users, and to introduce them to QA and
+development activities.
+
+Using complex scripts
+~~~~~~~~~~~~~~~~~~~~~
+
+In some cases like for kernel development it can be worth developing
+complex scripts to be able to fully automate bisecting.
+
+Here is what Ingo Molnar says about that <<7>>:
+
+_____________
+i have a fully automated bootup-hang bisection script. It is based on
+"git-bisect run". I run the script, it builds and boots kernels fully
+automatically, and when the bootup fails (the script notices that via
+the serial log, which it continuously watches - or via a timeout, if
+the system does not come up within 10 minutes it's a "bad" kernel),
+the script raises my attention via a beep and i power cycle the test
+box. (yeah, i should make use of a managed power outlet to 100%
+automate it)
+_____________
+
+Combining test suites, git bisect and other systems together
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+We have seen that test suites an git bisect are very powerful when
+used together. It can be even more powerful if you can combine them
+with other systems.
+
+For example some test suites could be run automatically at night with
+some unusual (or even random) configurations. And if a regression is
+found by a test suite, then "git bisect" can be automatically
+launched, and its result can be emailed to the author of the first bad
+commit found by "git bisect", and perhaps other people too. And a new
+entry in the bug tracking system could be automatically created too.
+
+
+The future of bisecting
+-----------------------
+
+"git replace"
+~~~~~~~~~~~~~
+
+We saw earlier that "git bisect skip" is now using a PRNG to try to
+avoid areas in the commit graph where commits are untestable. The
+problem is that sometimes the first bad commit will be in an
+untestable area.
+
+To simplify the discussion we will suppose that the untestable area is
+a simple string of commits and that it was created by a breakage
+introduced by one commit (let's call it BBC for bisect breaking
+commit) and later fixed by another one (let's call it BFC for bisect
+fixing commit).
+
+For example:
+
+-------------
+...-Y-BBC-X1-X2-X3-X4-X5-X6-BFC-Z-...
+-------------
+
+where we know that Y is good and BFC is bad, and where BBC and X1 to
+X6 are untestable.
+
+In this case if you are bisecting manually, what you can do is create
+a special branch that starts just before the BBC. The first commit in
+this branch should be the BBC with the BFC squashed into it. And the
+other commits in the branch should be the commits between BBC and BFC
+rebased on the first commit of the branch and then the commit after
+BFC also rebased on.
+
+For example:
+
+-------------
+ (BBC+BFC)-X1'-X2'-X3'-X4'-X5'-X6'-Z'
+ /
+...-Y-BBC-X1-X2-X3-X4-X5-X6-BFC-Z-...
+-------------
+
+where commits quoted with ' have been rebased.
+
+You can easily create such a branch with Git using interactive rebase.
+
+For example using:
+
+-------------
+$ git rebase -i Y Z
+-------------
+
+and then moving BFC after BBC and squashing it.
+
+After that you can start bisecting as usual in the new branch and you
+should eventually find the first bad commit.
+
+For example:
+
+-------------
+$ git bisect start Z' Y
+-------------
+
+If you are using "git bisect run", you can use the same manual fix up
+as above, and then start another "git bisect run" in the special
+branch. Or as the "git bisect" man page says, the script passed to
+"git bisect run" can apply a patch before it compiles and test the
+software <<8>>. The patch should turn a current untestable commits
+into a testable one. So the testing will result in "good" or "bad" and
+"git bisect" will be able to find the first bad commit. And the script
+should not forget to remove the patch once the testing is done before
+exiting from the script.
+
+(Note that instead of a patch you can use "git cherry-pick BFC" to
+apply the fix, and in this case you should use "git reset --hard
+HEAD^" to revert the cherry-pick after testing and before returning
+from the script.)
+
+But the above ways to work around untestable areas are a little bit
+clunky. Using special branches is nice because these branches can be
+shared by developers like usual branches, but the risk is that people
+will get many such branches. And it disrupts the normal "git bisect"
+work-flow. So, if you want to use "git bisect run" completely
+automatically, you have to add special code in your script to restart
+bisection in the special branches.
+
+Anyway one can notice in the above special branch example that the Z'
+and Z commits should point to the same source code state (the same
+"tree" in git parlance). That's because Z' result from applying the
+same changes as Z just in a slightly different order.
+
+So if we could just "replace" Z by Z' when we bisect, then we would
+not need to add anything to a script. It would just work for anyone in
+the project sharing the special branches and the replacements.
+
+With the example above that would give:
+
+-------------
+ (BBC+BFC)-X1'-X2'-X3'-X4'-X5'-X6'-Z'-...
+ /
+...-Y-BBC-X1-X2-X3-X4-X5-X6-BFC-Z
+-------------
+
+That's why the "git replace" command was created. Technically it
+stores replacements "refs" in the "refs/replace/" hierarchy. These
+"refs" are like branches (that are stored in "refs/heads/") or tags
+(that are stored in "refs/tags"), and that means that they can
+automatically be shared like branches or tags among developers.
+
+"git replace" is a very powerful mechanism. It can be used to fix
+commits in already released history, for example to change the commit
+message or the author. And it can also be used instead of git "grafts"
+to link a repository with another old repository.
+
+In fact it's this last feature that "sold" it to the git community, so
+it is now in the "master" branch of git's git repository and it should
+be released in git 1.6.5 in October or November 2009.
+
+One problem with "git replace" is that currently it stores all the
+replacements refs in "refs/replace/", but it would be perhaps better
+if the replacement refs that are useful only for bisecting would be in
+"refs/replace/bisect/". This way the replacement refs could be used
+only for bisecting, while other refs directly in "refs/replace/" would
+be used nearly all the time.
+
+Bisecting sporadic bugs
+~~~~~~~~~~~~~~~~~~~~~~~
+
+Another possible improvement to "git bisect" would be to optionally
+add some redundancy to the tests performed so that it would be more
+reliable when tracking sporadic bugs.
+
+This has been requested by some kernel developers because some bugs
+called sporadic bugs do not appear in all the kernel builds because
+they are very dependent on the compiler output.
+
+The idea is that every 3 test for example, "git bisect" could ask the
+user to test a commit that has already been found to be "good" or
+"bad" (because one of its descendants or one of its ancestors has been
+found to be "good" or "bad" respectively). If it happens that a commit
+has been previously incorrectly classified then the bisection can be
+aborted early, hopefully before too many mistakes have been made. Then
+the user will have to look at what happened and then restart the
+bisection using a fixed bisect log.
+
+There is already a project called BBChop created by Ealdwulf Wuffinga
+on Github that does something like that using Bayesian Search Theory
+<<9>>:
+
+_____________
+BBChop is like 'git bisect' (or equivalent), but works when your bug
+is intermittent. That is, it works in the presence of false negatives
+(when a version happens to work this time even though it contains the
+bug). It assumes that there are no false positives (in principle, the
+same approach would work, but adding it may be non-trivial).
+_____________
+
+But BBChop is independent of any VCS and it would be easier for Git
+users to have something integrated in Git.
+
+Conclusion
+----------
+
+We have seen that regressions are an important problem, and that "git
+bisect" has nice features that complement very well practices and
+other tools, especially test suites, that are generally used to fight
+regressions. But it might be needed to change some work-flows and
+(bad) habits to get the most out of it.
+
+Some improvements to the algorithms inside "git bisect" are possible
+and some new features could help in some cases, but overall "git
+bisect" works already very well, is used a lot, and is already very
+useful. To back up that last claim, let's give the final word to Ingo
+Molnar when he was asked by the author how much time does he think
+"git bisect" saves him when he uses it:
+
+_____________
+a _lot_.
+
+About ten years ago did i do my first 'bisection' of a Linux patch
+queue. That was prior the Git (and even prior the BitKeeper) days. I
+literally days spent sorting out patches, creating what in essence
+were standalone commits that i guessed to be related to that bug.
+
+It was a tool of absolute last resort. I'd rather spend days looking
+at printk output than do a manual 'patch bisection'.
+
+With Git bisect it's a breeze: in the best case i can get a ~15 step
+kernel bisection done in 20-30 minutes, in an automated way. Even with
+manual help or when bisecting multiple, overlapping bugs, it's rarely
+more than an hour.
+
+In fact it's invaluable because there are bugs i would never even
+_try_ to debug if it wasn't for git bisect. In the past there were bug
+patterns that were immediately hopeless for me to debug - at best i
+could send the crash/bug signature to lkml and hope that someone else
+can think of something.
+
+And even if a bisection fails today it tells us something valuable
+about the bug: that it's non-deterministic - timing or kernel image
+layout dependent.
+
+So git bisect is unconditional goodness - and feel free to quote that
+;-)
+_____________
+
+Acknowledgements
+----------------
+
+Many thanks to Junio Hamano for his help in reviewing this paper, for
+reviewing the patches I sent to the git mailing list, for discussing
+some ideas and helping me improve them, for improving "git bisect" a
+lot and for his awesome work in maintaining and developing Git.
+
+Many thanks to Ingo Molnar for giving me very useful information that
+appears in this paper, for commenting on this paper, for his
+suggestions to improve "git bisect" and for evangelizing "git bisect"
+on the linux kernel mailing lists.
+
+Many thanks to Linus Torvalds for inventing, developing and
+evangelizing "git bisect", Git and Linux.
+
+Many thanks to the many other great people who helped one way or
+another when I worked on git, especially to Andreas Ericsson, Johannes
+Schindelin, H. Peter Anvin, Daniel Barkalow, Bill Lear, John Hawley,
+Shawn O. Pierce, Jeff King, Sam Vilain, Jon Seymour.
+
+Many thanks to the Linux-Kongress program committee for choosing the
+author to given a talk and for publishing this paper.
+
+References
+----------
+
+- [[[1]]] http://www.nist.gov/public_affairs/releases/n02-10.htm['Software Errors Cost U.S. Economy $59.5 Billion Annually'. Nist News Release.]
+- [[[2]]] http://java.sun.com/docs/codeconv/html/CodeConventions.doc.html#16712['Code Conventions for the Java Programming Language'. Sun Microsystems.]
+- [[[3]]] http://en.wikipedia.org/wiki/Software_maintenance['Software maintenance'. Wikipedia.]
+- [[[4]]] http://article.gmane.org/gmane.comp.version-control.git/45195/[Junio C Hamano. 'Automated bisect success story'. Gmane.]
+- [[[5]]] http://lwn.net/Articles/317154/[Christian Couder. 'Fully automated bisecting with "git bisect run"'. LWN.net.]
+- [[[6]]] http://lwn.net/Articles/277872/[Jonathan Corbet. 'Bisection divides users and developers'. LWN.net.]
+- [[[7]]] http://article.gmane.org/gmane.linux.scsi/36652/[Ingo Molnar. 'Re: BUG 2.6.23-rc3 can't see sd partitions on Alpha'. Gmane.]
+- [[[8]]] http://www.kernel.org/pub/software/scm/git/docs/git-bisect.html[Junio C Hamano and the git-list. 'git-bisect(1) Manual Page'. Linux Kernel Archives.]
+- [[[9]]] http://github.com/Ealdwulf/bbchop[Ealdwulf. 'bbchop'. GitHub.]
diff --git a/Documentation/git-bisect.txt b/Documentation/git-bisect.txt
index d2ffae0..c39d957 100644
--- a/Documentation/git-bisect.txt
+++ b/Documentation/git-bisect.txt
@@ -330,6 +330,11 @@ Documentation
-------------
Documentation by Junio C Hamano and the git-list <git@vger.kernel.org>.
+SEE ALSO
+--------
+link:git-bisect-lk2009.html[Fighting regressions with git bisect],
+linkgit:git-blame[1].
+
GIT
---
Part of the linkgit:git[1] suite
diff --git a/Documentation/git-bundle.txt b/Documentation/git-bundle.txt
index aee7e4a..c3a066e 100644
--- a/Documentation/git-bundle.txt
+++ b/Documentation/git-bundle.txt
@@ -24,7 +24,7 @@ ssh, rsync, http) cannot be used. This command provides support for
'git-fetch' and 'git-pull' to operate by packaging objects and references
in an archive at the originating machine, then importing those into
another repository using 'git-fetch' and 'git-pull'
-after moving the archive by some means (i.e., by sneakernet). As no
+after moving the archive by some means (e.g., by sneakernet). As no
direct connection between the repositories exists, the user must specify a
basis for the bundle that is held by the destination repository: the
bundle assumes that all objects in the basis are already in the
diff --git a/Documentation/git-clone.txt b/Documentation/git-clone.txt
index 7e7d9fc..7ccd742 100644
--- a/Documentation/git-clone.txt
+++ b/Documentation/git-clone.txt
@@ -11,7 +11,7 @@ SYNOPSIS
[verse]
'git clone' [--template=<template_directory>]
[-l] [-s] [--no-hardlinks] [-q] [-n] [--bare] [--mirror]
- [-o <name>] [-u <upload-pack>] [--reference <repository>]
+ [-o <name>] [-b <name>] [-u <upload-pack>] [--reference <repository>]
[--depth <depth>] [--recursive] [--] <repository> [<directory>]
DESCRIPTION
diff --git a/Documentation/git-commit-tree.txt b/Documentation/git-commit-tree.txt
index b8834ba..4fec5d5 100644
--- a/Documentation/git-commit-tree.txt
+++ b/Documentation/git-commit-tree.txt
@@ -73,6 +73,7 @@ A commit comment is read from stdin. If a changelog
entry is not provided via "<" redirection, 'git-commit-tree' will just wait
for one to be entered and terminated with ^D.
+include::date-formats.txt[]
Diagnostics
-----------
diff --git a/Documentation/git-commit.txt b/Documentation/git-commit.txt
index 3ea80c8..5fb43f9 100644
--- a/Documentation/git-commit.txt
+++ b/Documentation/git-commit.txt
@@ -9,9 +9,9 @@ SYNOPSIS
--------
[verse]
'git commit' [-a | --interactive] [-s] [-v] [-u<mode>] [--amend] [--dry-run]
- [(-c | -C) <commit>] [-F <file> | -m <msg>]
+ [(-c | -C) <commit>] [-F <file> | -m <msg>] [--reset-author]
[--allow-empty] [--no-verify] [-e] [--author=<author>]
- [--cleanup=<mode>] [--] [[-i | -o ]<file>...]
+ [--date=<date>] [--cleanup=<mode>] [--] [[-i | -o ]<file>...]
DESCRIPTION
-----------
@@ -69,6 +69,25 @@ OPTIONS
Like '-C', but with '-c' the editor is invoked, so that
the user can further edit the commit message.
+--reset-author::
+ When used with -C/-c/--amend options, declare that the
+ authorship of the resulting commit now belongs of the committer.
+ This also renews the author timestamp.
+
+--short::
+ When doing a dry-run, give the output in the short-format. See
+ linkgit:git-status[1] for details. Implies `--dry-run`.
+
+--porcelain::
+ When doing a dry-run, give the output in a porcelain-ready
+ format. See linkgit:git-status[1] for details. Implies
+ `--dry-run`.
+
+-z::
+ When showing `short` or `porcelain` status output, terminate
+ entries in the status output with NUL, instead of LF. If no
+ format is given, implies the `--porcelain` output format.
+
-F <file>::
--file=<file>::
Take the commit message from the given file. Use '-' to
@@ -80,6 +99,9 @@ OPTIONS
an existing commit that matches the given string and its author
name is used.
+--date=<date>::
+ Override the author date used in the commit.
+
-m <msg>::
--message=<msg>::
Use the given <msg> as the commit message.
@@ -212,6 +234,8 @@ specified.
these files are also staged for the next commit on top
of what have been staged before.
+:git-commit: 1
+include::date-formats.txt[]
EXAMPLES
--------
diff --git a/Documentation/git-config.txt b/Documentation/git-config.txt
index f68b198..2632928 100644
--- a/Documentation/git-config.txt
+++ b/Documentation/git-config.txt
@@ -37,11 +37,12 @@ existing values that match the regexp are updated or unset. If
you want to handle the lines that do *not* match the regex, just
prepend a single exclamation mark in front (see also <<EXAMPLES>>).
-The type specifier can be either '--int' or '--bool', which will make
+The type specifier can be either '--int' or '--bool', to make
'git-config' ensure that the variable(s) are of the given type and
convert the value to the canonical form (simple decimal number for int,
-a "true" or "false" string for bool). If no type specifier is passed,
-no checks or transformations are performed on the value.
+a "true" or "false" string for bool), or '--path', which does some
+path expansion (see '--path' below). If no type specifier is passed, no
+checks or transformations are performed on the value.
The file-option can be one of '--system', '--global' or '--file'
which specify where the values will be read from or written to.
@@ -136,6 +137,13 @@ See also <<FILES>>.
'git-config' will ensure that the output matches the format of
either --bool or --int, as described above.
+--path::
+ 'git-config' will expand leading '{tilde}' to the value of
+ '$HOME', and '{tilde}user' to the home directory for the
+ specified user. This option has no effect when setting the
+ value (but you can use 'git config bla {tilde}/' from the
+ command line to let your shell do the expansion).
+
-z::
--null::
For all options that output values and/or keys, always
diff --git a/Documentation/git-cvsserver.txt b/Documentation/git-cvsserver.txt
index 99a7c14..fbab295 100644
--- a/Documentation/git-cvsserver.txt
+++ b/Documentation/git-cvsserver.txt
@@ -277,6 +277,21 @@ In `dbdriver` and `dbuser` you can use the following variables:
If no name can be determined, the
numeric uid is used.
+ENVIRONMENT
+-----------
+
+These variables obviate the need for command-line options in some
+circumstances, allowing easier restricted usage through git-shell.
+
+GIT_CVSSERVER_BASE_PATH takes the place of the argument to --base-path.
+
+GIT_CVSSERVER_ROOT specifies a single-directory whitelist. The
+repository must still be configured to allow access through
+git-cvsserver, as described above.
+
+When these environment variables are set, the corresponding
+command-line arguments may not be used.
+
Eclipse CVS Client Notes
------------------------
diff --git a/Documentation/git-fast-import.txt b/Documentation/git-fast-import.txt
index 288032c..e6d364f 100644
--- a/Documentation/git-fast-import.txt
+++ b/Documentation/git-fast-import.txt
@@ -311,8 +311,8 @@ change to the project.
....
'commit' SP <ref> LF
mark?
- ('author' SP <name> SP LT <email> GT SP <when> LF)?
- 'committer' SP <name> SP LT <email> GT SP <when> LF
+ ('author' (SP <name>)? SP LT <email> GT SP <when> LF)?
+ 'committer' (SP <name>)? SP LT <email> GT SP <when> LF
data
('from' SP <committish> LF)?
('merge' SP <committish> LF)?
@@ -657,7 +657,7 @@ lightweight (non-annotated) tags see the `reset` command below.
....
'tag' SP <name> LF
'from' SP <committish> LF
- 'tagger' SP <name> SP LT <email> GT SP <when> LF
+ 'tagger' (SP <name>)? SP LT <email> GT SP <when> LF
data
....
diff --git a/Documentation/git-mailinfo.txt b/Documentation/git-mailinfo.txt
index 996c3fc..b81ac98 100644
--- a/Documentation/git-mailinfo.txt
+++ b/Documentation/git-mailinfo.txt
@@ -8,7 +8,7 @@ git-mailinfo - Extracts patch and authorship from a single e-mail message
SYNOPSIS
--------
-'git mailinfo' [-k] [-u | --encoding=<encoding> | -n] [--scissors] <msg> <patch>
+'git mailinfo' [-k|-b] [-u | --encoding=<encoding> | -n] [--scissors] <msg> <patch>
DESCRIPTION
@@ -32,6 +32,11 @@ OPTIONS
munging, and is most useful when used to read back
'git-format-patch -k' output.
+-b::
+ When -k is not in effect, all leading strings bracketed with '['
+ and ']' pairs are stripped. This option limits the stripping to
+ only the pairs whose bracketed string contains the word "PATCH".
+
-u::
The commit log message, author name and author email are
taken from the e-mail, and after minimally decoding MIME
diff --git a/Documentation/git-push.txt b/Documentation/git-push.txt
index 52c0538..e3eb1e8 100644
--- a/Documentation/git-push.txt
+++ b/Documentation/git-push.txt
@@ -91,6 +91,10 @@ nor in any Push line of the corresponding remotes file---see below).
will be tab-separated and sent to stdout instead of stderr. The full
symbolic names of the refs will be given.
+--delete::
+ All listed refs are deleted from the remote repository. This is
+ the same as prefixing all refs with a colon.
+
--tags::
All refs under `$GIT_DIR/refs/tags` are pushed, in
addition to refspecs explicitly listed on the command
diff --git a/Documentation/git-remote-helpers.txt b/Documentation/git-remote-helpers.txt
index 8beb42d..5cfdc0c 100644
--- a/Documentation/git-remote-helpers.txt
+++ b/Documentation/git-remote-helpers.txt
@@ -79,6 +79,17 @@ style string if it contains an LF.
+
Supported if the helper has the "push" capability.
+'import' <name>::
+ Produces a fast-import stream which imports the current value
+ of the named ref. It may additionally import other refs as
+ needed to construct the history efficiently. The script writes
+ to a helper-specific private namespace. The value of the named
+ ref should be written to a location in this namespace derived
+ by applying the refspecs from the "refspec" capability to the
+ name of the ref.
++
+Supported if the helper has the "import" capability.
+
If a fatal error occurs, the program writes the error message to
stderr and exits. The caller should expect that a suitable error
message has been printed if the child closes the connection without
@@ -99,6 +110,19 @@ CAPABILITIES
'push'::
This helper supports the 'push' command.
+'import'::
+ This helper supports the 'import' command.
+
+'refspec' 'spec'::
+ When using the import command, expect the source ref to have
+ been written to the destination ref. The earliest applicable
+ refspec takes precedence. For example
+ "refs/heads/*:refs/svn/origin/branches/*" means that, after an
+ "import refs/heads/name", the script has written to
+ refs/svn/origin/branches/name. If this capability is used at
+ all, it must cover all refs reported by the list command; if
+ it is not used, it is effectively "*:*"
+
REF LIST ATTRIBUTES
-------------------
@@ -107,6 +131,10 @@ REF LIST ATTRIBUTES
commands. A helper might chose to acquire the ref list by
opening a different type of connection to the destination.
+'unchanged'::
+ This ref is unchanged since the last import or fetch, although
+ the helper cannot necessarily determine what value that produced.
+
OPTIONS
-------
'option verbosity' <N>::
diff --git a/Documentation/git-reset.txt b/Documentation/git-reset.txt
index 2d27e40..9df6de2 100644
--- a/Documentation/git-reset.txt
+++ b/Documentation/git-reset.txt
@@ -62,6 +62,7 @@ This means that `git reset -p` is the opposite of `git add -p` (see
linkgit:git-add[1]).
-q::
+--quiet::
Be quiet, only report errors.
<commit>::
diff --git a/Documentation/git-rm.txt b/Documentation/git-rm.txt
index 5afb1e7..c21d19e 100644
--- a/Documentation/git-rm.txt
+++ b/Documentation/git-rm.txt
@@ -12,13 +12,13 @@ SYNOPSIS
DESCRIPTION
-----------
Remove files from the index, or from the working tree and the index.
-'git-rm' will not remove a file from just your working directory.
-(There is no option to remove a file only from the work tree
+`git rm` will not remove a file from just your working directory.
+(There is no option to remove a file only from the working tree
and yet keep it in the index; use `/bin/rm` if you want to do that.)
The files being removed have to be identical to the tip of the branch,
and no updates to their contents can be staged in the index,
though that default behavior can be overridden with the `-f` option.
-When '--cached' is given, the staged content has to
+When `--cached` is given, the staged content has to
match either the tip of the branch or the file on disk,
allowing the file to be removed from just the index.
@@ -64,7 +64,7 @@ OPTIONS
-q::
--quiet::
- 'git-rm' normally outputs one line (in the form of an "rm" command)
+ `git rm` normally outputs one line (in the form of an `rm` command)
for each file removed. This option suppresses that output.
@@ -81,6 +81,58 @@ two directories `d` and `d2`, there is a difference between
using `git rm \'d\*\'` and `git rm \'d/\*\'`, as the former will
also remove all of directory `d2`.
+REMOVING FILES THAT HAVE DISAPPEARED FROM THE FILESYSTEM
+--------------------------------------------------------
+There is no option for `git rm` to remove from the index only
+the paths that have disappeared from the filesystem. However,
+depending on the use case, there are several ways that can be
+done.
+
+Using "git commit -a"
+~~~~~~~~~~~~~~~~~~~~~
+If you intend that your next commit should record all modifications
+of tracked files in the working tree and record all removals of
+files that have been removed from the working tree with `rm`
+(as opposed to `git rm`), use `git commit -a`, as it will
+automatically notice and record all removals. You can also have a
+similar effect without committing by using `git add -u`.
+
+Using "git add -A"
+~~~~~~~~~~~~~~~~~~
+When accepting a new code drop for a vendor branch, you probably
+want to record both the removal of paths and additions of new paths
+as well as modifications of existing paths.
+
+Typically you would first remove all tracked files from the working
+tree using this command:
+
+----------------
+git ls-files -z | xargs -0 rm -f
+----------------
+
+and then "untar" the new code in the working tree. Alternately
+you could "rsync" the changes into the working tree.
+
+After that, the easiest way to record all removals, additions, and
+modifications in the working tree is:
+
+----------------
+git add -A
+----------------
+
+See linkgit:git-add[1].
+
+Other ways
+~~~~~~~~~~
+If all you really want to do is to remove from the index the files
+that are no longer present in the working tree (perhaps because
+your working tree is dirty so that you cannot use `git commit -a`),
+use the following command:
+
+----------------
+git diff --name-only --diff-filter=D -z | xargs -0 git rm --cached
+----------------
+
EXAMPLES
--------
git rm Documentation/\\*.txt::
diff --git a/Documentation/git-send-email.txt b/Documentation/git-send-email.txt
index c85d7f4..ced35b2 100644
--- a/Documentation/git-send-email.txt
+++ b/Documentation/git-send-email.txt
@@ -84,7 +84,7 @@ See the CONFIGURATION section for 'sendemail.multiedit'.
--in-reply-to=<identifier>::
Specify the contents of the first In-Reply-To header.
Subsequent emails will refer to the previous email
- instead of this if --chain-reply-to is set (the default)
+ instead of this if --chain-reply-to is set.
Only necessary if --compose is also set. If --compose
is not set, this will be prompted for.
@@ -108,9 +108,10 @@ Sending
--envelope-sender=<address>::
Specify the envelope sender used to send the emails.
This is useful if your default address is not the address that is
- subscribed to a list. If you use the sendmail binary, you must have
- suitable privileges for the -f parameter. Default is the value of
- the 'sendemail.envelopesender' configuration variable; if that is
+ subscribed to a list. In order to use the 'From' address, set the
+ value to "auto". If you use the sendmail binary, you must have
+ suitable privileges for the -f parameter. Default is the value of the
+ 'sendemail.envelopesender' configuration variable; if that is
unspecified, choosing the envelope sender is left to your MTA.
--smtp-encryption=<encryption>::
@@ -171,8 +172,8 @@ Automating
email sent. If disabled with "--no-chain-reply-to", all emails after
the first will be sent as replies to the first email sent. When using
this, it is recommended that the first file given be an overview of the
- entire patch series. Default is the value of the 'sendemail.chainreplyto'
- configuration value; if that is unspecified, default to --chain-reply-to.
+ entire patch series. Disabled by default, but the 'sendemail.chainreplyto'
+ configuration variable can be used to enable it.
--identity=<identity>::
A configuration identity. When given, causes values in the
diff --git a/Documentation/git-status.txt b/Documentation/git-status.txt
index 84f60f3..b3dfa42 100644
--- a/Documentation/git-status.txt
+++ b/Documentation/git-status.txt
@@ -8,7 +8,7 @@ git-status - Show the working tree status
SYNOPSIS
--------
-'git status' <options>...
+'git status' [<options>...] [--] [<pathspec>...]
DESCRIPTION
-----------
@@ -20,25 +20,90 @@ are what you _would_ commit by running `git commit`; the second and
third are what you _could_ commit by running 'git-add' before running
`git commit`.
-The command takes the same set of options as 'git-commit'; it
-shows what would be committed if the same options are given to
-'git-commit'.
-
-If there is no path that is different between the index file and
-the current HEAD commit (i.e., there is nothing to commit by running
-`git commit`), the command exits with non-zero status.
+OPTIONS
+-------
+
+-s::
+--short::
+ Give the output in the short-format.
+
+--porcelain::
+ Give the output in a stable, easy-to-parse format for scripts.
+ Currently this is identical to --short output, but is guaranteed
+ not to change in the future, making it safe for scripts.
+
+-u[<mode>]::
+--untracked-files[=<mode>]::
+ Show untracked files (Default: 'all').
++
+The mode parameter is optional, and is used to specify
+the handling of untracked files. The possible options are:
++
+--
+ - 'no' - Show no untracked files
+ - 'normal' - Shows untracked files and directories
+ - 'all' - Also shows individual files in untracked directories.
+--
++
+See linkgit:git-config[1] for configuration variable
+used to change the default for when the option is not
+specified.
+
+-z::
+ Terminate entries with NUL, instead of LF. This implies
+ the `--porcelain` output format if no other format is given.
OUTPUT
------
The output from this command is designed to be used as a commit
template comment, and all the output lines are prefixed with '#'.
+The default, long format, is designed to be human readable,
+verbose and descriptive. They are subject to change in any time.
The paths mentioned in the output, unlike many other git commands, are
made relative to the current directory if you are working in a
subdirectory (this is on purpose, to help cutting and pasting). See
the status.relativePaths config option below.
+In short-format, the status of each path is shown as
+
+ XY PATH1 -> PATH2
+
+where `PATH1` is the path in the `HEAD`, and ` -> PATH2` part is
+shown only when `PATH1` corresponds to a different path in the
+index/worktree (i.e. renamed).
+
+For unmerged entries, `X` shows the status of stage #2 (i.e. ours) and `Y`
+shows the status of stage #3 (i.e. theirs).
+
+For entries that do not have conflicts, `X` shows the status of the index,
+and `Y` shows the status of the work tree. For untracked paths, `XY` are
+`??`.
+
+ X Y Meaning
+ -------------------------------------------------
+ [MD] not updated
+ M [ MD] updated in index
+ A [ MD] added to index
+ D [ MD] deleted from index
+ R [ MD] renamed in index
+ C [ MD] copied in index
+ [MARC] index and work tree matches
+ [ MARC] M work tree changed since index
+ [ MARC] D deleted in work tree
+ -------------------------------------------------
+ D D unmerged, both deleted
+ A U unmerged, added by us
+ U D unmerged, deleted by them
+ U A unmerged, added by them
+ D U unmerged, deleted by us
+ A A unmerged, both added
+ U U unmerged, both modified
+ -------------------------------------------------
+ ? ? untracked
+ -------------------------------------------------
+
CONFIGURATION
-------------
@@ -53,9 +118,9 @@ paths shown are relative to the repository root, not to the current
directory.
If `status.submodulesummary` is set to a non zero number or true (identical
-to -1 or an unlimited number), the submodule summary will be enabled and a
-summary of commits for modified submodules will be shown (see --summary-limit
-option of linkgit:git-submodule[1]).
+to -1 or an unlimited number), the submodule summary will be enabled for
+the long format and a summary of commits for modified submodules will be
+shown (see --summary-limit option of linkgit:git-submodule[1]).
SEE ALSO
--------
@@ -63,8 +128,7 @@ linkgit:gitignore[5]
Author
------
-Written by Linus Torvalds <torvalds@osdl.org> and
-Junio C Hamano <gitster@pobox.com>.
+Written by Junio C Hamano <gitster@pobox.com>.
Documentation
--------------
diff --git a/Documentation/git-upload-pack.txt b/Documentation/git-upload-pack.txt
index 63f3b5c..b8e49dc 100644
--- a/Documentation/git-upload-pack.txt
+++ b/Documentation/git-upload-pack.txt
@@ -20,8 +20,6 @@ The UI for the protocol is on the 'git-fetch-pack' side, and the
program pair is meant to be used to pull updates from a remote
repository. For push operations, see 'git-send-pack'.
-After finishing the operation successfully, `post-upload-pack`
-hook is called (see linkgit:githooks[5]).
OPTIONS
-------
diff --git a/Documentation/git.txt b/Documentation/git.txt
index 8e577cc..352c230 100644
--- a/Documentation/git.txt
+++ b/Documentation/git.txt
@@ -43,9 +43,18 @@ unreleased) version of git, that is available from 'master'
branch of the `git.git` repository.
Documentation for older releases are available here:
-* link:v1.6.5.3/git.html[documentation for release 1.6.5.3]
+* link:v1.6.6/git.html[documentation for release 1.6.6]
* release notes for
+ link:RelNotes-1.6.6.txt[1.6.6].
+
+* link:v1.6.5.7/git.html[documentation for release 1.6.5.7]
+
+* release notes for
+ link:RelNotes-1.6.5.7.txt[1.6.5.7],
+ link:RelNotes-1.6.5.6.txt[1.6.5.6],
+ link:RelNotes-1.6.5.5.txt[1.6.5.5],
+ link:RelNotes-1.6.5.4.txt[1.6.5.4],
link:RelNotes-1.6.5.3.txt[1.6.5.3],
link:RelNotes-1.6.5.2.txt[1.6.5.2],
link:RelNotes-1.6.5.1.txt[1.6.5.1],
diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt
index 1f472ce..5a45e51 100644
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -197,6 +197,25 @@ intent is that if someone unsets the filter driver definition,
or does not have the appropriate filter program, the project
should still be usable.
+For example, in .gitattributes, you would assign the `filter`
+attribute for paths.
+
+------------------------
+*.c filter=indent
+------------------------
+
+Then you would define a "filter.indent.clean" and "filter.indent.smudge"
+configuration in your .git/config to specify a pair of commands to
+modify the contents of C programs when the source files are checked
+in ("clean" is run) and checked out (no change is made because the
+command is "cat").
+
+------------------------
+[filter "indent"]
+ clean = indent
+ smudge = cat
+------------------------
+
Interaction between checkin/checkout attributes
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
diff --git a/Documentation/gitcore-tutorial.txt b/Documentation/gitcore-tutorial.txt
index e237394..f762dca 100644
--- a/Documentation/gitcore-tutorial.txt
+++ b/Documentation/gitcore-tutorial.txt
@@ -602,7 +602,7 @@ $ git tag -s <tagname>
----------------
which will sign the current `HEAD` (but you can also give it another
-argument that specifies the thing to tag, i.e., you could have tagged the
+argument that specifies the thing to tag, e.g., you could have tagged the
current `mybranch` point by using `git tag <tagname> mybranch`).
You normally only do signed tags for major releases or things
diff --git a/Documentation/githooks.txt b/Documentation/githooks.txt
index 4cc3d13..29eeae7 100644
--- a/Documentation/githooks.txt
+++ b/Documentation/githooks.txt
@@ -310,35 +310,6 @@ Both standard output and standard error output are forwarded to
'git-send-pack' on the other end, so you can simply `echo` messages
for the user.
-post-upload-pack
-----------------
-
-After upload-pack successfully finishes its operation, this hook is called
-for logging purposes.
-
-The hook is passed various pieces of information, one per line, from its
-standard input. Currently the following items can be fed to the hook, but
-more types of information may be added in the future:
-
-want SHA-1::
- 40-byte hexadecimal object name the client asked to include in the
- resulting pack. Can occur one or more times in the input.
-
-have SHA-1::
- 40-byte hexadecimal object name the client asked to exclude from
- the resulting pack, claiming to have them already. Can occur zero
- or more times in the input.
-
-time float::
- Number of seconds spent for creating the packfile.
-
-size decimal::
- Size of the resulting packfile in bytes.
-
-kind string:
- Either "clone" (when the client did not give us any "have", and asked
- for all our refs with "want"), or "fetch" (otherwise).
-
pre-auto-gc
~~~~~~~~~~~
diff --git a/Documentation/manpage-base-url.xsl.in b/Documentation/manpage-base-url.xsl.in
new file mode 100644
index 0000000..e800904
--- /dev/null
+++ b/Documentation/manpage-base-url.xsl.in
@@ -0,0 +1,10 @@
+<!-- manpage-base-url.xsl:
+ special settings for manpages rendered from newer docbook -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+ version="1.0">
+
+<!-- set a base URL for relative links -->
+<xsl:param name="man.base.url.for.relative.links"
+ >@@MAN_BASE_URL@@</xsl:param>
+
+</xsl:stylesheet>
diff --git a/Documentation/pretty-formats.txt b/Documentation/pretty-formats.txt
index 0683fb3..53a9168 100644
--- a/Documentation/pretty-formats.txt
+++ b/Documentation/pretty-formats.txt
@@ -144,6 +144,14 @@ insert an empty string unless we are traversing reflog entries (e.g., by
`git log -g`). The `%d` placeholder will use the "short" decoration
format if `--decorate` was not already provided on the command line.
+If you add a `{plus}` (plus sign) after '%' of a placeholder, a line-feed
+is inserted immediately before the expansion if and only if the
+placeholder expands to a non-empty string.
+
+If you add a `-` (minus sign) after '%' of a placeholder, line-feeds that
+immediately precede the expansion are deleted if and only if the
+placeholder expands to an empty string.
+
* 'tformat:'
+
The 'tformat:' format works exactly like 'format:', except that it
diff --git a/Documentation/technical/api-hash.txt b/Documentation/technical/api-hash.txt
index c784d3e..e5061e0 100644
--- a/Documentation/technical/api-hash.txt
+++ b/Documentation/technical/api-hash.txt
@@ -1,6 +1,52 @@
hash API
========
-Talk about <hash.h>
+The hash API is a collection of simple hash table functions. Users are expected
+to implement their own hashing.
-(Linus)
+Data Structures
+---------------
+
+`struct hash_table`::
+
+ The hash table structure. The `array` member points to the hash table
+ entries. The `size` member counts the total number of valid and invalid
+ entries in the table. The `nr` member keeps track of the number of
+ valid entries.
+
+`struct hash_table_entry`::
+
+ An opaque structure representing an entry in the hash table. The `hash`
+ member is the entry's hash key and the `ptr` member is the entry's
+ value.
+
+Functions
+---------
+
+`init_hash`::
+
+ Initialize the hash table.
+
+`free_hash`::
+
+ Release memory associated with the hash table.
+
+`insert_hash`::
+
+ Insert a pointer into the hash table. If an entry with that hash
+ already exists, a pointer to the existing entry's value is returned.
+ Otherwise NULL is returned. This allows callers to implement
+ chaining, etc.
+
+`lookup_hash`::
+
+ Lookup an entry in the hash table. If an entry with that hash exists
+ the entry's value is returned. Otherwise NULL is returned.
+
+`for_each_hash`::
+
+ Call a function for each entry in the hash table. The function is
+ expected to take the entry's value as its only argument and return an
+ int. If the function returns a negative int the loop is aborted
+ immediately. Otherwise, the return value is accumulated and the sum
+ returned upon completion of the loop.
diff --git a/Documentation/technical/api-strbuf.txt b/Documentation/technical/api-strbuf.txt
index 7438149..a0e0f85 100644
--- a/Documentation/technical/api-strbuf.txt
+++ b/Documentation/technical/api-strbuf.txt
@@ -12,7 +12,7 @@ strbuf API actually relies on the string being free of NULs.
strbufs has some invariants that are very important to keep in mind:
-. The `buf` member is never NULL, so you it can be used in any usual C
+. The `buf` member is never NULL, so it can be used in any usual C
string operations safely. strbuf's _have_ to be initialized either by
`strbuf_init()` or by `= STRBUF_INIT` before the invariants, though.
+
@@ -55,7 +55,7 @@ Data structures
* `struct strbuf`
-This is string buffer structure. The `len` member can be used to
+This is the string buffer structure. The `len` member can be used to
determine the current length of the string, and `buf` member provides access to
the string itself.
@@ -253,3 +253,9 @@ same behaviour as well.
comments are considered contents to be removed or not.
`launch_editor`::
+
+ Launch the user preferred editor to edit a file and fill the buffer
+ with the file's contents upon the user completing their editing. The
+ third argument can be used to set the environment which the editor is
+ run in. If the buffer is NULL the editor is launched as usual but the
+ file's contents are not read into the buffer upon completion.