Merge branch 'jc/pickaxe'

Documentation/git-pickaxe.txt

@@ -0,0 +1,162 @@
+git-pickaxe(1)
+==============
+
+NAME
+----
+git-pickaxe - Show what revision and author last modified each line of a file
+
+SYNOPSIS
+--------
+[verse]
+'git-pickaxe' [-c] [-l] [-t] [-f] [-n] [-p] [-L n,m] [-S <revs-file>]
+              [-M] [-C] [-C] [--since=<date>] [<rev>] [--] <file>
+
+DESCRIPTION
+-----------
+
+Annotates each line in the given file with information from the revision which
+last modified the line. Optionally, start annotating from the given revision.
+
+Also it can limit the range of lines annotated.
+
+This report doesn't tell you anything about lines which have been deleted or
+replaced; you need to use a tool such as gitlink:git-diff[1] or the "pickaxe"
+interface briefly mentioned in the following paragraph.
+
+Apart from supporting file annotation, git also supports searching the
+development history for when a code snippet occured in a change. This makes it
+possible to track when a code snippet was added to a file, moved or copied
+between files, and eventually deleted or replaced. It works by searching for
+a text string in the diff. A small example:
+
+-----------------------------------------------------------------------------
+$ git log --pretty=oneline -S'blame_usage'
+5040f17eba15504bad66b14a645bddd9b015ebb7 blame -S <ancestry-file>
+ea4c7f9bf69e781dd0cd88d2bccb2bf5cc15c9a7 git-blame: Make the output
+-----------------------------------------------------------------------------
+
+OPTIONS
+-------
+-c, --compatibility::
+	Use the same output mode as gitlink:git-annotate[1] (Default: off).
+
+-L n,m::
+	Annotate only the specified line range (lines count from 1).
+
+-l, --long::
+	Show long rev (Default: off).
+
+-t, --time::
+	Show raw timestamp (Default: off).
+
+-S, --rev-file <revs-file>::
+	Use revs from revs-file instead of calling gitlink:git-rev-list[1].
+
+-f, --show-name::
+	Show filename in the original commit.  By default
+	filename is shown if there is any line that came from a
+	file with different name, due to rename detection.
+
+-n, --show-number::
+	Show line number in the original commit (Default: off).
+
+-p, --porcelain::
+	Show in a format designed for machine consumption.
+
+-M::
+	Detect moving lines in the file as well.  When a commit
+	moves a block of lines in a file (e.g. the original file
+	has A and then B, and the commit changes it to B and
+	then A), traditional 'blame' algorithm typically blames
+	the lines that were moved up (i.e. B) to the parent and
+	assigns blame to the lines that were moved down (i.e. A)
+	to the child commit.  With this option, both groups of
+	lines are blamed on the parent.
+
+-C::
+	In addition to `-M`, detect lines copied from other
+	files that were modified in the same commit.  This is
+	useful when you reorganize your program and move code
+	around across files.  When this option is given twice,
+	the command looks for copies from all other files in the
+	parent for the commit that creates the file in addition.
+
+-h, --help::
+	Show help message.
+
+
+THE PORCELAIN FORMAT
+--------------------
+
+In this format, each line is output after a header; the
+header at the minumum has the first line which has:
+
+- 40-byte SHA-1 of the commit the line is attributed to;
+- the line number of the line in the original file;
+- the line number of the line in the final file;
+- on a line that starts a group of line from a different
+  commit than the previous one, the number of lines in this
+  group.  On subsequent lines this field is absent.
+
+This header line is followed by the following information
+at least once for each commit:
+
+- author name ("author"), email ("author-mail"), time
+  ("author-time"), and timezone ("author-tz"); similarly
+  for committer.
+- filename in the commit the line is attributed to.
+- the first line of the commit log message ("summary").
+
+The contents of the actual line is output after the above
+header, prefixed by a TAB. This is to allow adding more
+header elements later.
+
+
+SPECIFIYING RANGES
+------------------
+
+Unlike `git-blame` and `git-annotate` in older git, the extent
+of annotation can be limited to both line ranges and revision
+ranges.  When you are interested in finding the origin for
+ll. 40-60 for file `foo`, you can use `-L` option like this:
+
+	git pickaxe -L 40,60 foo
+
+When you are not interested in changes older than the version
+v2.6.18, or changes older than 3 weeks, you can use revision
+range specifiers  similar to `git-rev-list`:
+
+	git pickaxe v2.6.18.. -- foo
+	git pickaxe --since=3.weeks -- foo
+
+When revision range specifiers are used to limit the annotation,
+lines that have not changed since the range boundary (either the
+commit v2.6.18 or the most recent commit that is more than 3
+weeks old in the above example) are blamed for that range
+boundary commit.
+
+A particularly useful way is to see if an added file have lines
+created by copy-and-paste from existing files.  Sometimes this
+indicates that the developer was being sloppy and did not
+refactor the code properly.  You can first find the commit that
+introduced the file with:
+
+	git log --diff-filter=A --pretty=short -- foo
+
+and then annotate the change between the commit and its
+parents, using `commit{caret}!` notation:
+
+	git pickaxe -C -C -f $commit^! -- foo
+
+
+SEE ALSO
+--------
+gitlink:git-blame[1]
+
+AUTHOR
+------
+Written by Junio C Hamano <junkio@cox.net>
+
+GIT
+---
+Part of the gitlink:git[7] suite

Documentation/git-rev-parse.txt

@@ -239,14 +239,21 @@ of `r1` and `r2` and is defined as
 It it the set of commits that are reachable from either one of
 `r1` or `r2` but not from both.
 
-Here are a few examples:
+Two other shorthands for naming a set that is formed by a commit
+and its parent commits exists.  `r1{caret}@` notation means all
+parents of `r1`.  `r1{caret}!` includes commit `r1` but excludes
+its all parents.
+
+Here are a handful examples:
 
    D                A B D
    D F              A B C D F
-   ^A G		    B D
+   ^A G             B D
    ^A F             B C F
    G...I            C D F G I
-   ^B G I	    C D F G I
+   ^B G I           C D F G I
+   F^@              A B C
+   F^! H            D F H
 
 Author
 ------

Documentation/git.txt

@@ -254,6 +254,9 @@ gitlink:git-annotate[1]::
 gitlink:git-blame[1]::
 	Blame file lines on commits.
 
+gitlink:git-pickaxe[1]::
+	Find out where each line in a file came from.
+
 gitlink:git-check-ref-format[1]::
 	Make sure ref name is well formed.
 

Makefile

@@ -290,6 +290,7 @@ BUILTIN_OBJS = \
 	builtin-mv.o \
 	builtin-name-rev.o \
 	builtin-pack-objects.o \
+	builtin-pickaxe.o \
 	builtin-prune.o \
 	builtin-prune-packed.o \
 	builtin-push.o \

blame.c

@@ -67,6 +67,7 @@ static void get_blob(struct commit *commit);
 static int num_get_patch;
 static int num_commits;
 static int patch_time;
+static int num_read_blob;
 
 struct blame_diff_state {
 	struct xdiff_emit_state xm;
@@ -206,6 +207,7 @@ static void get_blob(struct commit *commit)
 		return;
 
 	info->buf = read_sha1_file(info->sha1, type, &info->size);
+	num_read_blob++;
 
 	assert(!strcmp(type, blob_type));
 }
@@ -1076,6 +1078,7 @@ int main(int argc, const char **argv)
 	}
 
 	if (DEBUG) {
+		printf("num read blob: %d\n", num_read_blob);
 		printf("num get patch: %d\n", num_get_patch);
 		printf("num commits: %d\n", num_commits);
 		printf("patch time: %f\n", patch_time / 1000000.0);

builtin.h

@@ -44,6 +44,7 @@ extern int cmd_mailsplit(int argc, const char **argv, const char *prefix);
 extern int cmd_mv(int argc, const char **argv, const char *prefix);
 extern int cmd_name_rev(int argc, const char **argv, const char *prefix);
 extern int cmd_pack_objects(int argc, const char **argv, const char *prefix);
+extern int cmd_pickaxe(int argc, const char **argv, const char *prefix);
 extern int cmd_prune(int argc, const char **argv, const char *prefix);
 extern int cmd_prune_packed(int argc, const char **argv, const char *prefix);
 extern int cmd_push(int argc, const char **argv, const char *prefix);

diff.h

@@ -46,6 +46,7 @@ struct diff_options {
 	const char *filter;
 	const char *orderfile;
 	const char *pickaxe;
+	const char *single_follow;
 	unsigned recursive:1,
 		 tree_in_recursive:1,
 		 binary:1,

diffcore-rename.c

@@ -256,11 +256,15 @@ void diffcore_rename(struct diff_options *options)
 
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
-		if (!DIFF_FILE_VALID(p->one))
+		if (!DIFF_FILE_VALID(p->one)) {
 			if (!DIFF_FILE_VALID(p->two))
 				continue; /* unmerged */
+			else if (options->single_follow &&
+				 strcmp(options->single_follow, p->two->path))
+				continue; /* not interested */
 			else
 				locate_rename_dst(p->two, 1);
+		}
 		else if (!DIFF_FILE_VALID(p->two)) {
 			/* If the source is a broken "delete", and
 			 * they did not really want to get broken,

git.c

@@ -249,6 +249,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp)
 		{ "mv", cmd_mv, RUN_SETUP },
 		{ "name-rev", cmd_name_rev, RUN_SETUP },
 		{ "pack-objects", cmd_pack_objects, RUN_SETUP },
+		{ "pickaxe", cmd_pickaxe, RUN_SETUP | USE_PAGER },
 		{ "prune", cmd_prune, RUN_SETUP },
 		{ "prune-packed", cmd_prune_packed, RUN_SETUP },
 		{ "push", cmd_push, RUN_SETUP },

revision.c

@@ -657,6 +657,13 @@ int handle_revision_arg(const char *arg, struct rev_info *revs,
 			return 0;
 		*dotdot = '^';
 	}
+	dotdot = strstr(arg, "^!");
+	if (dotdot && !dotdot[2]) {
+		*dotdot = 0;
+		if (!add_parents_only(revs, arg, flags ^ UNINTERESTING))
+			*dotdot = '^';
+	}
+
 	local_flags = 0;
 	if (*arg == '^') {
 		local_flags = UNINTERESTING;

t/annotate-tests.sh

@@ -4,6 +4,7 @@
 check_count () {
 	head=
 	case "$1" in -h) head="$2"; shift; shift ;; esac
+	echo "$PROG file $head" >&4
 	$PROG file $head >.result || return 1
 	cat .result | perl -e '
 		my %expect = (@ARGV);

t/t8003-pickaxe.sh

@@ -0,0 +1,9 @@
+#!/bin/sh
+
+test_description='git-pickaxe'
+. ./test-lib.sh
+
+PROG='git pickaxe -c'
+. ../annotate-tests.sh
+
+test_done