Merge branch 'js/blame-lib'

The internal logic used in "git blame" has been libified to make it
easier to use by cgit.

* js/blame-lib: (29 commits)
  blame: move entry prepend to libgit
  blame: move scoreboard setup to libgit
  blame: move scoreboard-related methods to libgit
  blame: move fake-commit-related methods to libgit
  blame: move origin-related methods to libgit
  blame: move core structures to header
  blame: create entry prepend function
  blame: create scoreboard setup function
  blame: create scoreboard init function
  blame: rework methods that determine 'final' commit
  blame: wrap blame_sort and compare_blame_final
  blame: move progress updates to a scoreboard callback
  blame: make sanity_check use a callback in scoreboard
  blame: move no_whole_file_rename flag to scoreboard
  blame: move xdl_opts flags to scoreboard
  blame: move show_root flag to scoreboard
  blame: move reverse flag to scoreboard
  blame: move contents_from to scoreboard
  blame: move copy/move thresholds to scoreboard
  blame: move stat counters to scoreboard
  ...

Makefile

@@ -720,6 +720,7 @@ LIB_OBJS += argv-array.o
 LIB_OBJS += attr.o
 LIB_OBJS += base85.o
 LIB_OBJS += bisect.o
+LIB_OBJS += blame.o
 LIB_OBJS += blob.o
 LIB_OBJS += branch.o
 LIB_OBJS += bulk-checkin.o

blame.h

+#ifndef BLAME_H
+#define BLAME_H
+
+#include "cache.h"
+#include "commit.h"
+#include "xdiff-interface.h"
+#include "revision.h"
+#include "prio-queue.h"
+#include "diff.h"
+
+#define PICKAXE_BLAME_MOVE		01
+#define PICKAXE_BLAME_COPY		02
+#define PICKAXE_BLAME_COPY_HARDER	04
+#define PICKAXE_BLAME_COPY_HARDEST	010
+
+#define BLAME_DEFAULT_MOVE_SCORE	20
+#define BLAME_DEFAULT_COPY_SCORE	40
+
+/*
+ * One blob in a commit that is being suspected
+ */
+struct blame_origin {
+	int refcnt;
+	/* Record preceding blame record for this blob */
+	struct blame_origin *previous;
+	/* origins are put in a list linked via `next' hanging off the
+	 * corresponding commit's util field in order to make finding
+	 * them fast.  The presence in this chain does not count
+	 * towards the origin's reference count.  It is tempting to
+	 * let it count as long as the commit is pending examination,
+	 * but even under circumstances where the commit will be
+	 * present multiple times in the priority queue of unexamined
+	 * commits, processing the first instance will not leave any
+	 * work requiring the origin data for the second instance.  An
+	 * interspersed commit changing that would have to be
+	 * preexisting with a different ancestry and with the same
+	 * commit date in order to wedge itself between two instances
+	 * of the same commit in the priority queue _and_ produce
+	 * blame entries relevant for it.  While we don't want to let
+	 * us get tripped up by this case, it certainly does not seem
+	 * worth optimizing for.
+	 */
+	struct blame_origin *next;
+	struct commit *commit;
+	/* `suspects' contains blame entries that may be attributed to
+	 * this origin's commit or to parent commits.  When a commit
+	 * is being processed, all suspects will be moved, either by
+	 * assigning them to an origin in a different commit, or by
+	 * shipping them to the scoreboard's ent list because they
+	 * cannot be attributed to a different commit.
+	 */
+	struct blame_entry *suspects;
+	mmfile_t file;
+	struct object_id blob_oid;
+	unsigned mode;
+	/* guilty gets set when shipping any suspects to the final
+	 * blame list instead of other commits
+	 */
+	char guilty;
+	char path[FLEX_ARRAY];
+};
+
+/*
+ * Each group of lines is described by a blame_entry; it can be split
+ * as we pass blame to the parents.  They are arranged in linked lists
+ * kept as `suspects' of some unprocessed origin, or entered (when the
+ * blame origin has been finalized) into the scoreboard structure.
+ * While the scoreboard structure is only sorted at the end of
+ * processing (according to final image line number), the lists
+ * attached to an origin are sorted by the target line number.
+ */
+struct blame_entry {
+	struct blame_entry *next;
+
+	/* the first line of this group in the final image;
+	 * internally all line numbers are 0 based.
+	 */
+	int lno;
+
+	/* how many lines this group has */
+	int num_lines;
+
+	/* the commit that introduced this group into the final image */
+	struct blame_origin *suspect;
+
+	/* the line number of the first line of this group in the
+	 * suspect's file; internally all line numbers are 0 based.
+	 */
+	int s_lno;
+
+	/* how significant this entry is -- cached to avoid
+	 * scanning the lines over and over.
+	 */
+	unsigned score;
+};
+
+/*
+ * The current state of the blame assignment.
+ */
+struct blame_scoreboard {
+	/* the final commit (i.e. where we started digging from) */
+	struct commit *final;
+	/* Priority queue for commits with unassigned blame records */
+	struct prio_queue commits;
+	struct rev_info *revs;
+	const char *path;
+
+	/*
+	 * The contents in the final image.
+	 * Used by many functions to obtain contents of the nth line,
+	 * indexed with scoreboard.lineno[blame_entry.lno].
+	 */
+	const char *final_buf;
+	unsigned long final_buf_size;
+
+	/* linked list of blames */
+	struct blame_entry *ent;
+
+	/* look-up a line in the final buffer */
+	int num_lines;
+	int *lineno;
+
+	/* stats */
+	int num_read_blob;
+	int num_get_patch;
+	int num_commits;
+
+	/*
+	 * blame for a blame_entry with score lower than these thresholds
+	 * is not passed to the parent using move/copy logic.
+	 */
+	unsigned move_score;
+	unsigned copy_score;
+
+	/* use this file's contents as the final image */
+	const char *contents_from;
+
+	/* flags */
+	int reverse;
+	int show_root;
+	int xdl_opts;
+	int no_whole_file_rename;
+	int debug;
+
+	/* callbacks */
+	void(*on_sanity_fail)(struct blame_scoreboard *, int);
+	void(*found_guilty_entry)(struct blame_entry *, void *);
+
+	void *found_guilty_entry_data;
+};
+
+/*
+ * Origin is refcounted and usually we keep the blob contents to be
+ * reused.
+ */
+static inline struct blame_origin *blame_origin_incref(struct blame_origin *o)
+{
+	if (o)
+		o->refcnt++;
+	return o;
+}
+extern void blame_origin_decref(struct blame_origin *o);
+
+extern void blame_coalesce(struct blame_scoreboard *sb);
+extern void blame_sort_final(struct blame_scoreboard *sb);
+extern unsigned blame_entry_score(struct blame_scoreboard *sb, struct blame_entry *e);
+extern void assign_blame(struct blame_scoreboard *sb, int opt);
+extern const char *blame_nth_line(struct blame_scoreboard *sb, long lno);
+
+extern void init_scoreboard(struct blame_scoreboard *sb);
+extern void setup_scoreboard(struct blame_scoreboard *sb, const char *path, struct blame_origin **orig);
+
+extern struct blame_entry *blame_entry_prepend(struct blame_entry *head, long start, long end, struct blame_origin *o);
+
+#endif /* BLAME_H */

builtin.h

@@ -25,8 +25,6 @@ struct fmt_merge_msg_opts {
 extern int fmt_merge_msg(struct strbuf *in, struct strbuf *out,
 			 struct fmt_merge_msg_opts *);
 
-extern int textconv_object(const char *path, unsigned mode, const struct object_id *oid, int oid_valid, char **buf, unsigned long *buf_size);
-
 extern int is_builtin(const char *s);
 
 extern int cmd_add(int argc, const char **argv, const char *prefix);

builtin/cat-file.c

@@ -5,6 +5,7 @@
  */
 #include "cache.h"
 #include "builtin.h"
+#include "diff.h"
 #include "parse-options.h"
 #include "userdiff.h"
 #include "streaming.h"

diff.c

@@ -5270,6 +5270,29 @@ size_t fill_textconv(struct userdiff_driver *driver,
 	return size;
 }
 
+int textconv_object(const char *path,
+		    unsigned mode,
+		    const struct object_id *oid,
+		    int oid_valid,
+		    char **buf,
+		    unsigned long *buf_size)
+{
+	struct diff_filespec *df;
+	struct userdiff_driver *textconv;
+
+	df = alloc_filespec(path);
+	fill_filespec(df, oid->hash, oid_valid, mode);
+	textconv = get_textconv(df);
+	if (!textconv) {
+		free_filespec(df);
+		return 0;
+	}
+
+	*buf_size = fill_textconv(textconv, df, buf);
+	free_filespec(df);
+	return 1;
+}
+
 void setup_diff_pager(struct diff_options *opt)
 {
 	/*

diff.h

@@ -385,6 +385,13 @@ extern size_t fill_textconv(struct userdiff_driver *driver,
  */
 extern struct userdiff_driver *get_textconv(struct diff_filespec *one);
 
+/*
+ * Prepare diff_filespec and convert it using diff textconv API
+ * if the textconv driver exists.
+ * Return 1 if the conversion succeeds, 0 otherwise.
+ */
+extern int textconv_object(const char *path, unsigned mode, const struct object_id *oid, int oid_valid, char **buf, unsigned long *buf_size);
+
 extern int parse_rename_score(const char **cp_p);
 
 extern long parse_algorithm_value(const char *value);