[PATCH] Introducing software archaeologist's tool "pickaxe".

This steals the "pickaxe" feature from JIT and make it available
to the bare Plumbing layer.  From the command line, the user
gives a string he is intersted in.

Using the diff-core infrastructure previously introduced, it
filters the differences to limit the output only to the diffs
between <src> and <dst> where the string appears only in one but
not in the other.  For example:

 $ ./git-rev-list HEAD | ./git-diff-tree -Sdiff-tree-helper --stdin -M

would show the diffs that touch the string "diff-tree-helper".

In real software-archaeologist application, you would typically
look for a few to several lines of code and see where that code
came from.

The "pickaxe" module runs after "rename/copy detection" module,
so it even crosses the file rename boundary, as the above
example demonstrates.

Signed-off-by: Junio C Hamano <junkio@cox.net>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 56 insertions, 0 deletions

diff --git a/diffcore-pickaxe.c b/diffcore-pickaxe.c
new file mode 100644
index 0000000000..ee22e36abc
--- /dev/null
+++ b/diffcore-pickaxe.c
@@ -0,0 +1,56 @@
+/*
+ * Copyright (C) 2005 Junio C Hamano
+ */
+#include "cache.h"
+#include "diff.h"
+#include "diffcore.h"
+#include "delta.h"
+
+static int contains(struct diff_filespec *one,
+		    const char *needle, unsigned long len)
+{
+	unsigned long offset, sz;
+	const char *data;
+	if (diff_populate_filespec(one))
+		return 0;
+	sz = one->size;
+	data = one->data;
+	for (offset = 0; offset + len <= sz; offset++)
+		     if (!strncmp(needle, data + offset, len))
+			     return 1;
+	return 0;
+}
+
+void diff_pickaxe(struct diff_queue_struct *q, const char *needle)
+{
+	unsigned long len = strlen(needle);
+	int i;
+	struct diff_queue_struct outq;
+	outq.queue = NULL;
+	outq.nr = outq.alloc = 0;
+
+	for (i = 0; i < q->nr; i++) {
+		struct diff_filepair *p = q->queue[i];
+		if (!p->one->file_valid) {
+			if (!p->two->file_valid)
+				continue; /* ignore nonsense */
+			/* created */
+			if (contains(p->two, needle, len))
+				diff_queue(&outq, p->one, p->two);
+		}
+		else if (!p->two->file_valid) {
+			if (contains(p->one, needle, len))
+				diff_queue(&outq, p->one, p->two);
+		}
+		else if (contains(p->one, needle, len) !=
+			 contains(p->two, needle, len))
+			diff_queue(&outq, p->one, p->two);
+	}
+	for (i = 0; i < q->nr; i++) {
+		struct diff_filepair *p = q->queue[i];
+		free(p);
+	}
+	free(q->queue);
+	*q = outq;
+	return;
+}