Add range-diff, a tbdiff lookalike

.gitignore

@@ -113,6 +113,7 @@
 /git-pull
 /git-push
 /git-quiltimport
+/git-range-diff
 /git-read-tree
 /git-rebase
 /git-rebase--am

Documentation/git-range-diff.txt

@@ -0,0 +1,10 @@
+git-range-diff(1)
+=================
+
+NAME
+----
+git-range-diff - Compare two commit ranges (e.g. two versions of a branch)
+
+GIT
+---
+Part of the linkgit:git[1] suite

Makefile

@@ -870,6 +870,7 @@ LIB_OBJS += gpg-interface.o
 LIB_OBJS += graph.o
 LIB_OBJS += grep.o
 LIB_OBJS += hashmap.o
+LIB_OBJS += linear-assignment.o
 LIB_OBJS += help.o
 LIB_OBJS += hex.o
 LIB_OBJS += ident.o
@@ -924,6 +925,7 @@ LIB_OBJS += progress.o
 LIB_OBJS += prompt.o
 LIB_OBJS += protocol.o
 LIB_OBJS += quote.o
+LIB_OBJS += range-diff.o
 LIB_OBJS += reachable.o
 LIB_OBJS += read-cache.o
 LIB_OBJS += reflog-walk.o
@@ -1062,6 +1064,7 @@ BUILTIN_OBJS += builtin/prune-packed.o
 BUILTIN_OBJS += builtin/prune.o
 BUILTIN_OBJS += builtin/pull.o
 BUILTIN_OBJS += builtin/push.o
+BUILTIN_OBJS += builtin/range-diff.o
 BUILTIN_OBJS += builtin/read-tree.o
 BUILTIN_OBJS += builtin/rebase--helper.o
 BUILTIN_OBJS += builtin/receive-pack.o

builtin.h

@@ -201,6 +201,7 @@ 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_pull(int argc, const char **argv, const char *prefix);
 extern int cmd_push(int argc, const char **argv, const char *prefix);
+extern int cmd_range_diff(int argc, const char **argv, const char *prefix);
 extern int cmd_read_tree(int argc, const char **argv, const char *prefix);
 extern int cmd_rebase__helper(int argc, const char **argv, const char *prefix);
 extern int cmd_receive_pack(int argc, const char **argv, const char *prefix);

builtin/range-diff.c

@@ -0,0 +1,68 @@
+#include "cache.h"
+#include "builtin.h"
+#include "parse-options.h"
+#include "range-diff.h"
+
+static const char * const builtin_range_diff_usage[] = {
+N_("git range-diff [<options>] <old-base>..<old-tip> <new-base>..<new-tip>"),
+N_("git range-diff [<options>] <old-tip>...<new-tip>"),
+N_("git range-diff [<options>] <base> <old-tip> <new-tip>"),
+NULL
+};
+
+int cmd_range_diff(int argc, const char **argv, const char *prefix)
+{
+	int creation_factor = 60;
+	struct option options[] = {
+		OPT_INTEGER(0, "creation-factor", &creation_factor,
+			    N_("Percentage by which creation is weighted")),
+		OPT_END()
+	};
+	int res = 0;
+	struct strbuf range1 = STRBUF_INIT, range2 = STRBUF_INIT;
+
+	argc = parse_options(argc, argv, NULL, options,
+			     builtin_range_diff_usage, 0);
+
+	if (argc == 2) {
+		if (!strstr(argv[0], ".."))
+			die(_("no .. in range: '%s'"), argv[0]);
+		strbuf_addstr(&range1, argv[0]);
+
+		if (!strstr(argv[1], ".."))
+			die(_("no .. in range: '%s'"), argv[1]);
+		strbuf_addstr(&range2, argv[1]);
+	} else if (argc == 3) {
+		strbuf_addf(&range1, "%s..%s", argv[0], argv[1]);
+		strbuf_addf(&range2, "%s..%s", argv[0], argv[2]);
+	} else if (argc == 1) {
+		const char *b = strstr(argv[0], "..."), *a = argv[0];
+		int a_len;
+
+		if (!b) {
+			error(_("single arg format must be symmetric range"));
+			usage_with_options(builtin_range_diff_usage, options);
+		}
+
+		a_len = (int)(b - a);
+		if (!a_len) {
+			a = "HEAD";
+			a_len = strlen(a);
+		}
+		b += 3;
+		if (!*b)
+			b = "HEAD";
+		strbuf_addf(&range1, "%s..%.*s", b, a_len, a);
+		strbuf_addf(&range2, "%.*s..%s", a_len, a, b);
+	} else {
+		error(_("need two commit ranges"));
+		usage_with_options(builtin_range_diff_usage, options);
+	}
+
+	res = show_range_diff(range1.buf, range2.buf, creation_factor);
+
+	strbuf_release(&range1);
+	strbuf_release(&range2);
+
+	return res;
+}

command-list.txt

@@ -139,6 +139,7 @@ git-prune-packed                        plumbingmanipulators
 git-pull                                mainporcelain           remote
 git-push                                mainporcelain           remote
 git-quiltimport                         foreignscminterface
+git-range-diff                          mainporcelain
 git-read-tree                           plumbingmanipulators
 git-rebase                              mainporcelain           history
 git-receive-pack                        synchelpers

git.c

@@ -520,6 +520,7 @@ static struct cmd_struct commands[] = {
 	{ "prune-packed", cmd_prune_packed, RUN_SETUP },
 	{ "pull", cmd_pull, RUN_SETUP | NEED_WORK_TREE },
 	{ "push", cmd_push, RUN_SETUP },
+	{ "range-diff", cmd_range_diff, RUN_SETUP | USE_PAGER },
 	{ "read-tree", cmd_read_tree, RUN_SETUP | SUPPORT_SUPER_PREFIX},
 	{ "rebase--helper", cmd_rebase__helper, RUN_SETUP | NEED_WORK_TREE },
 	{ "receive-pack", cmd_receive_pack },

linear-assignment.c

@@ -0,0 +1,201 @@
+/*
+ * Based on: Jonker, R., & Volgenant, A. (1987). <i>A shortest augmenting path
+ * algorithm for dense and sparse linear assignment problems</i>. Computing,
+ * 38(4), 325-340.
+ */
+#include "cache.h"
+#include "linear-assignment.h"
+
+#define COST(column, row) cost[(column) + column_count * (row)]
+
+/*
+ * The parameter `cost` is the cost matrix: the cost to assign column j to row
+ * i is `cost[j + column_count * i].
+ */
+void compute_assignment(int column_count, int row_count, int *cost,
+			int *column2row, int *row2column)
+{
+	int *v, *d;
+	int *free_row, free_count = 0, saved_free_count, *pred, *col;
+	int i, j, phase;
+
+	memset(column2row, -1, sizeof(int) * column_count);
+	memset(row2column, -1, sizeof(int) * row_count);
+	ALLOC_ARRAY(v, column_count);
+
+	/* column reduction */
+	for (j = column_count - 1; j >= 0; j--) {
+		int i1 = 0;
+
+		for (i = 1; i < row_count; i++)
+			if (COST(j, i1) > COST(j, i))
+				i1 = i;
+		v[j] = COST(j, i1);
+		if (row2column[i1] == -1) {
+			/* row i1 unassigned */
+			row2column[i1] = j;
+			column2row[j] = i1;
+		} else {
+			if (row2column[i1] >= 0)
+				row2column[i1] = -2 - row2column[i1];
+			column2row[j] = -1;
+		}
+	}
+
+	/* reduction transfer */
+	ALLOC_ARRAY(free_row, row_count);
+	for (i = 0; i < row_count; i++) {
+		int j1 = row2column[i];
+		if (j1 == -1)
+			free_row[free_count++] = i;
+		else if (j1 < -1)
+			row2column[i] = -2 - j1;
+		else {
+			int min = COST(!j1, i) - v[!j1];
+			for (j = 1; j < column_count; j++)
+				if (j != j1 && min > COST(j, i) - v[j])
+					min = COST(j, i) - v[j];
+			v[j1] -= min;
+		}
+	}
+
+	if (free_count ==
+	    (column_count < row_count ? row_count - column_count : 0)) {
+		free(v);
+		free(free_row);
+		return;
+	}
+
+	/* augmenting row reduction */
+	for (phase = 0; phase < 2; phase++) {
+		int k = 0;
+
+		saved_free_count = free_count;
+		free_count = 0;
+		while (k < saved_free_count) {
+			int u1, u2;
+			int j1 = 0, j2, i0;
+
+			i = free_row[k++];
+			u1 = COST(j1, i) - v[j1];
+			j2 = -1;
+			u2 = INT_MAX;
+			for (j = 1; j < column_count; j++) {
+				int c = COST(j, i) - v[j];
+				if (u2 > c) {
+					if (u1 < c) {
+						u2 = c;
+						j2 = j;
+					} else {
+						u2 = u1;
+						u1 = c;
+						j2 = j1;
+						j1 = j;
+					}
+				}
+			}
+			if (j2 < 0) {
+				j2 = j1;
+				u2 = u1;
+			}
+
+			i0 = column2row[j1];
+			if (u1 < u2)
+				v[j1] -= u2 - u1;
+			else if (i0 >= 0) {
+				j1 = j2;
+				i0 = column2row[j1];
+			}
+
+			if (i0 >= 0) {
+				if (u1 < u2)
+					free_row[--k] = i0;
+				else
+					free_row[free_count++] = i0;
+			}
+			row2column[i] = j1;
+			column2row[j1] = i;
+		}
+	}
+
+	/* augmentation */
+	saved_free_count = free_count;
+	ALLOC_ARRAY(d, column_count);
+	ALLOC_ARRAY(pred, column_count);
+	ALLOC_ARRAY(col, column_count);
+	for (free_count = 0; free_count < saved_free_count; free_count++) {
+		int i1 = free_row[free_count], low = 0, up = 0, last, k;
+		int min, c, u1;
+
+		for (j = 0; j < column_count; j++) {
+			d[j] = COST(j, i1) - v[j];
+			pred[j] = i1;
+			col[j] = j;
+		}
+
+		j = -1;
+		do {
+			last = low;
+			min = d[col[up++]];
+			for (k = up; k < column_count; k++) {
+				j = col[k];
+				c = d[j];
+				if (c <= min) {
+					if (c < min) {
+						up = low;
+						min = c;
+					}
+					col[k] = col[up];
+					col[up++] = j;
+				}
+			}
+			for (k = low; k < up; k++)
+				if (column2row[col[k]] == -1)
+					goto update;
+
+			/* scan a row */
+			do {
+				int j1 = col[low++];
+
+				i = column2row[j1];
+				u1 = COST(j1, i) - v[j1] - min;
+				for (k = up; k < column_count; k++) {
+					j = col[k];
+					c = COST(j, i) - v[j] - u1;
+					if (c < d[j]) {
+						d[j] = c;
+						pred[j] = i;
+						if (c == min) {
+							if (column2row[j] == -1)
+								goto update;
+							col[k] = col[up];
+							col[up++] = j;
+						}
+					}
+				}
+			} while (low != up);
+		} while (low == up);
+
+update:
+		/* updating of the column pieces */
+		for (k = 0; k < last; k++) {
+			int j1 = col[k];
+			v[j1] += d[j1] - min;
+		}
+
+		/* augmentation */
+		do {
+			if (j < 0)
+				BUG("negative j: %d", j);
+			i = pred[j];
+			column2row[j] = i;
+			SWAP(j, row2column[i]);
+		} while (i1 != i);
+	}
+
+	free(col);
+	free(pred);
+	free(d);
+	free(v);
+	free(free_row);
+}

linear-assignment.h

@@ -0,0 +1,22 @@
+#ifndef LINEAR_ASSIGNMENT_H
+#define LINEAR_ASSIGNMENT_H
+
+/*
+ * Compute an assignment of columns -> rows (and vice versa) such that every
+ * column is assigned to at most one row (and vice versa) minimizing the
+ * overall cost.
+ *
+ * The parameter `cost` is the cost matrix: the cost to assign column j to row
+ * i is `cost[j + column_count * i].
+ *
+ * The arrays column2row and row2column will be populated with the respective
+ * assignments (-1 for unassigned, which can happen only if column_count !=
+ * row_count).
+ */
+void compute_assignment(int column_count, int row_count, int *cost,
+			int *column2row, int *row2column);
+
+/* The maximal cost in the cost matrix (to prevent integer overflows). */
+#define COST_MAX (1<<16)
+
+#endif