#include "quote.h"
#include "xdiff-interface.h"
#include "cache-tree.h"
-#include "path-list.h"
+#include "string-list.h"
#include "mailmap.h"
#include "parse-options.h"
-static char blame_usage[] = "git-blame [options] [rev-opts] [rev] [--] file";
+static char blame_usage[] = "git blame [options] [rev-opts] [rev] [--] file";
static const char *blame_opt_usage[] = {
blame_usage,
"",
- "[rev-opts] are documented in git-rev-parse(1)",
+ "[rev-opts] are documented in git-rev-list(1)",
NULL
};
static int reverse;
static int blank_boundary;
static int incremental;
-static int cmd_is_annotate;
static int xdl_opts = XDF_NEED_MINIMAL;
-static struct path_list mailmap;
+static struct string_list mailmap;
#ifndef DEBUG
#define DEBUG 0
*/
char guilty;
+ /* true if the entry has been scanned for copies in the current parent
+ */
+ char scanned;
+
/* the line number of the first line of this group in the
* suspect's file; internally all line numbers are 0 based.
*/
return porigin;
}
-/*
- * Parsing of patch chunks...
- */
-struct chunk {
- /* line number in postimage; up to but not including this
- * line is the same as preimage
- */
- int same;
-
- /* preimage line number after this chunk */
- int p_next;
-
- /* postimage line number after this chunk */
- int t_next;
-};
-
-struct patch {
- struct chunk *chunks;
- int num;
-};
-
-struct blame_diff_state {
- struct xdiff_emit_state xm;
- struct patch *ret;
- unsigned hunk_post_context;
- unsigned hunk_in_pre_context : 1;
-};
-
-static void process_u_diff(void *state_, char *line, unsigned long len)
-{
- struct blame_diff_state *state = state_;
- struct chunk *chunk;
- int off1, off2, len1, len2, num;
-
- num = state->ret->num;
- if (len < 4 || line[0] != '@' || line[1] != '@') {
- if (state->hunk_in_pre_context && line[0] == ' ')
- state->ret->chunks[num - 1].same++;
- else {
- state->hunk_in_pre_context = 0;
- if (line[0] == ' ')
- state->hunk_post_context++;
- else
- state->hunk_post_context = 0;
- }
- return;
- }
-
- if (num && state->hunk_post_context) {
- chunk = &state->ret->chunks[num - 1];
- chunk->p_next -= state->hunk_post_context;
- chunk->t_next -= state->hunk_post_context;
- }
- state->ret->num = ++num;
- state->ret->chunks = xrealloc(state->ret->chunks,
- sizeof(struct chunk) * num);
- chunk = &state->ret->chunks[num - 1];
- if (parse_hunk_header(line, len, &off1, &len1, &off2, &len2)) {
- state->ret->num--;
- return;
- }
-
- /* Line numbers in patch output are one based. */
- off1--;
- off2--;
-
- chunk->same = len2 ? off2 : (off2 + 1);
-
- chunk->p_next = off1 + (len1 ? len1 : 1);
- chunk->t_next = chunk->same + len2;
- state->hunk_in_pre_context = 1;
- state->hunk_post_context = 0;
-}
-
-static struct patch *compare_buffer(mmfile_t *file_p, mmfile_t *file_o,
- int context)
-{
- struct blame_diff_state state;
- xpparam_t xpp;
- xdemitconf_t xecfg;
- xdemitcb_t ecb;
-
- xpp.flags = xdl_opts;
- memset(&xecfg, 0, sizeof(xecfg));
- xecfg.ctxlen = context;
- ecb.outf = xdiff_outf;
- ecb.priv = &state;
- memset(&state, 0, sizeof(state));
- state.xm.consume = process_u_diff;
- state.ret = xmalloc(sizeof(struct patch));
- state.ret->chunks = NULL;
- state.ret->num = 0;
-
- xdi_diff(file_p, file_o, &xpp, &xecfg, &ecb);
-
- if (state.ret->num) {
- struct chunk *chunk;
- chunk = &state.ret->chunks[state.ret->num - 1];
- chunk->p_next -= state.hunk_post_context;
- chunk->t_next -= state.hunk_post_context;
- }
- return state.ret;
-}
-
-/*
- * Run diff between two origins and grab the patch output, so that
- * we can pass blame for lines origin is currently suspected for
- * to its parent.
- */
-static struct patch *get_patch(struct origin *parent, struct origin *origin)
-{
- mmfile_t file_p, file_o;
- struct patch *patch;
-
- fill_origin_blob(parent, &file_p);
- fill_origin_blob(origin, &file_o);
- if (!file_p.ptr || !file_o.ptr)
- return NULL;
- patch = compare_buffer(&file_p, &file_o, 0);
- num_get_patch++;
- return patch;
-}
-
-static void free_patch(struct patch *p)
-{
- free(p->chunks);
- free(p);
-}
-
/*
* Link in a new blame entry to the scoreboard. Entries that cover the
* same line range have been removed from the scoreboard previously.
}
}
+struct blame_chunk_cb_data {
+ struct scoreboard *sb;
+ struct origin *target;
+ struct origin *parent;
+ long plno;
+ long tlno;
+};
+
+static void blame_chunk_cb(void *data, long same, long p_next, long t_next)
+{
+ struct blame_chunk_cb_data *d = data;
+ blame_chunk(d->sb, d->tlno, d->plno, same, d->target, d->parent);
+ d->plno = p_next;
+ d->tlno = t_next;
+}
+
/*
* We are looking at the origin 'target' and aiming to pass blame
* for the lines it is suspected to its parent. Run diff to find
struct origin *target,
struct origin *parent)
{
- int i, last_in_target, plno, tlno;
- struct patch *patch;
+ int last_in_target;
+ mmfile_t file_p, file_o;
+ struct blame_chunk_cb_data d = { sb, target, parent, 0, 0 };
+ xpparam_t xpp;
+ xdemitconf_t xecfg;
last_in_target = find_last_in_target(sb, target);
if (last_in_target < 0)
return 1; /* nothing remains for this target */
- patch = get_patch(parent, target);
- plno = tlno = 0;
- for (i = 0; i < patch->num; i++) {
- struct chunk *chunk = &patch->chunks[i];
+ fill_origin_blob(parent, &file_p);
+ fill_origin_blob(target, &file_o);
+ num_get_patch++;
- blame_chunk(sb, tlno, plno, chunk->same, target, parent);
- plno = chunk->p_next;
- tlno = chunk->t_next;
- }
+ memset(&xpp, 0, sizeof(xpp));
+ xpp.flags = xdl_opts;
+ memset(&xecfg, 0, sizeof(xecfg));
+ xecfg.ctxlen = 0;
+ xdi_diff_hunks(&file_p, &file_o, blame_chunk_cb, &d, &xpp, &xecfg);
/* The rest (i.e. anything after tlno) are the same as the parent */
- blame_chunk(sb, tlno, plno, last_in_target, target, parent);
+ blame_chunk(sb, d.tlno, d.plno, last_in_target, target, parent);
- free_patch(patch);
return 0;
}
}
}
+struct handle_split_cb_data {
+ struct scoreboard *sb;
+ struct blame_entry *ent;
+ struct origin *parent;
+ struct blame_entry *split;
+ long plno;
+ long tlno;
+};
+
+static void handle_split_cb(void *data, long same, long p_next, long t_next)
+{
+ struct handle_split_cb_data *d = data;
+ handle_split(d->sb, d->ent, d->tlno, d->plno, same, d->parent, d->split);
+ d->plno = p_next;
+ d->tlno = t_next;
+}
+
/*
* Find the lines from parent that are the same as ent so that
* we can pass blames to it. file_p has the blob contents for
const char *cp;
int cnt;
mmfile_t file_o;
- struct patch *patch;
- int i, plno, tlno;
+ struct handle_split_cb_data d = { sb, ent, parent, split, 0, 0 };
+ xpparam_t xpp;
+ xdemitconf_t xecfg;
/*
* Prepare mmfile that contains only the lines in ent.
}
file_o.size = cp - file_o.ptr;
- patch = compare_buffer(file_p, &file_o, 1);
-
/*
* file_o is a part of final image we are annotating.
* file_p partially may match that image.
*/
+ memset(&xpp, 0, sizeof(xpp));
+ xpp.flags = xdl_opts;
+ memset(&xecfg, 0, sizeof(xecfg));
+ xecfg.ctxlen = 1;
memset(split, 0, sizeof(struct blame_entry [3]));
- plno = tlno = 0;
- for (i = 0; i < patch->num; i++) {
- struct chunk *chunk = &patch->chunks[i];
-
- handle_split(sb, ent, tlno, plno, chunk->same, parent, split);
- plno = chunk->p_next;
- tlno = chunk->t_next;
- }
+ xdi_diff_hunks(file_p, &file_o, handle_split_cb, &d, &xpp, &xecfg);
/* remainder, if any, all match the preimage */
- handle_split(sb, ent, tlno, plno, ent->num_lines, parent, split);
- free_patch(patch);
+ handle_split(sb, ent, d.tlno, d.plno, ent->num_lines, parent, split);
}
/*
while (made_progress) {
made_progress = 0;
for (e = sb->ent; e; e = e->next) {
- if (e->guilty || !same_suspect(e->suspect, target))
+ if (e->guilty || !same_suspect(e->suspect, target) ||
+ ent_score(sb, e) < blame_move_score)
continue;
find_copy_in_blob(sb, e, parent, split, &file_p);
if (split[1].suspect &&
*/
static struct blame_list *setup_blame_list(struct scoreboard *sb,
struct origin *target,
+ int min_score,
int *num_ents_p)
{
struct blame_entry *e;
struct blame_list *blame_list = NULL;
for (e = sb->ent, num_ents = 0; e; e = e->next)
- if (!e->guilty && same_suspect(e->suspect, target))
+ if (!e->scanned && !e->guilty &&
+ same_suspect(e->suspect, target) &&
+ min_score < ent_score(sb, e))
num_ents++;
if (num_ents) {
blame_list = xcalloc(num_ents, sizeof(struct blame_list));
for (e = sb->ent, i = 0; e; e = e->next)
- if (!e->guilty && same_suspect(e->suspect, target))
+ if (!e->scanned && !e->guilty &&
+ same_suspect(e->suspect, target) &&
+ min_score < ent_score(sb, e))
blame_list[i++].ent = e;
}
*num_ents_p = num_ents;
return blame_list;
}
+/*
+ * Reset the scanned status on all entries.
+ */
+static void reset_scanned_flag(struct scoreboard *sb)
+{
+ struct blame_entry *e;
+ for (e = sb->ent; e; e = e->next)
+ e->scanned = 0;
+}
+
/*
* For lines target is suspected for, see if we can find code movement
* across file boundary from the parent commit. porigin is the path
struct blame_list *blame_list;
int num_ents;
- blame_list = setup_blame_list(sb, target, &num_ents);
+ blame_list = setup_blame_list(sb, target, blame_copy_score, &num_ents);
if (!blame_list)
return 1; /* nothing remains for this target */
if (!DIFF_FILE_VALID(p->one))
continue; /* does not exist in parent */
+ if (S_ISGITLINK(p->one->mode))
+ continue; /* ignore git links */
if (porigin && !strcmp(p->one->path, porigin->path))
/* find_move already dealt with this path */
continue;
split_blame(sb, split, blame_list[j].ent);
made_progress = 1;
}
+ else
+ blame_list[j].ent->scanned = 1;
decref_split(split);
}
free(blame_list);
if (!made_progress)
break;
- blame_list = setup_blame_list(sb, target, &num_ents);
+ blame_list = setup_blame_list(sb, target, blame_copy_score, &num_ents);
if (!blame_list) {
retval = 1;
break;
}
}
+ reset_scanned_flag(sb);
diff_flush(&diff_opts);
diff_tree_release_paths(&diff_opts);
return retval;
int detailed)
{
int len;
- char *tmp, *endp;
+ char *tmp, *endp, *reencoded, *message;
static char author_buf[1024];
static char committer_buf[1024];
static char summary_buf[1024];
die("Cannot read commit %s",
sha1_to_hex(commit->object.sha1));
}
+ reencoded = reencode_commit_message(commit, NULL);
+ message = reencoded ? reencoded : commit->buffer;
ret->author = author_buf;
- get_ac_line(commit->buffer, "\nauthor ",
+ get_ac_line(message, "\nauthor ",
sizeof(author_buf), author_buf, &ret->author_mail,
&ret->author_time, &ret->author_tz);
- if (!detailed)
+ if (!detailed) {
+ free(reencoded);
return;
+ }
ret->committer = committer_buf;
- get_ac_line(commit->buffer, "\ncommitter ",
+ get_ac_line(message, "\ncommitter ",
sizeof(committer_buf), committer_buf, &ret->committer_mail,
&ret->committer_time, &ret->committer_tz);
ret->summary = summary_buf;
- tmp = strstr(commit->buffer, "\n\n");
+ tmp = strstr(message, "\n\n");
if (!tmp) {
error_out:
sprintf(summary_buf, "(%s)", sha1_to_hex(commit->object.sha1));
+ free(reencoded);
return;
}
tmp += 2;
goto error_out;
memcpy(summary_buf, tmp, len);
summary_buf[len] = 0;
+ free(reencoded);
}
/*
if (suspect->commit->object.flags & UNINTERESTING) {
if (blank_boundary)
memset(hex, ' ', length);
- else if (!cmd_is_annotate) {
+ else if (!(opt & OUTPUT_ANNOTATE_COMPAT)) {
length--;
putchar('^');
}
/*
* Add phony grafts for use with -S; this is primarily to
- * support git-cvsserver that wants to give a linear history
+ * support git's cvsserver that wants to give a linear history
* to its clients.
*/
static int read_ancestry(const char *graft_file)
* Used for the command line parsing; check if the path exists
* in the working tree.
*/
-static int has_path_in_work_tree(const char *path)
+static int has_string_in_work_tree(const char *path)
{
struct stat st;
return !lstat(path, &st);
struct commit *commit;
struct origin *origin;
unsigned char head_sha1[20];
- struct strbuf buf;
+ struct strbuf buf = STRBUF_INIT;
const char *ident;
time_t now;
int size, len;
origin = make_origin(commit, path);
- strbuf_init(&buf, 0);
if (!contents_from || strcmp("-", contents_from)) {
struct stat st;
const char *read_from;
- unsigned long fin_size;
if (contents_from) {
if (stat(contents_from, &st) < 0)
die("Cannot lstat %s", path);
read_from = path;
}
- fin_size = xsize_t(st.st_size);
mode = canon_mode(st.st_mode);
switch (st.st_mode & S_IFMT) {
case S_IFREG:
die("cannot open or read %s", read_from);
break;
case S_IFLNK:
- if (readlink(read_from, buf.buf, buf.alloc) != fin_size)
+ if (strbuf_readlink(&buf, read_from, st.st_size) < 0)
die("cannot readlink %s", read_from);
- buf.len = fin_size;
break;
default:
die("unsupported file type %s", read_from);
struct scoreboard sb;
struct origin *o;
struct blame_entry *ent;
- int i, seen_dashdash, unk;
- long bottom, top, lno;
+ long dashdash_pos, bottom, top, lno;
const char *final_commit_name = NULL;
enum object_type type;
};
struct parse_opt_ctx_t ctx;
-
- cmd_is_annotate = !strcmp(argv[0], "annotate");
+ int cmd_is_annotate = !strcmp(argv[0], "annotate");
git_config(git_blame_config, NULL);
init_revisions(&revs, NULL);
save_commit_buffer = 0;
+ dashdash_pos = 0;
parse_options_start(&ctx, argc, argv, PARSE_OPT_KEEP_DASHDASH |
PARSE_OPT_KEEP_ARGV0);
for (;;) {
- int n;
-
switch (parse_options_step(&ctx, options, blame_opt_usage)) {
case PARSE_OPT_HELP:
exit(129);
case PARSE_OPT_DONE:
+ if (ctx.argv[0])
+ dashdash_pos = ctx.cpidx;
goto parse_done;
}
ctx.argv[0] = "--children";
reverse = 1;
}
- n = handle_revision_opt(&revs, ctx.argc, ctx.argv,
- &ctx.cpidx, ctx.out);
- if (n <= 0) {
- error("unknown option `%s'", ctx.argv[0]);
- usage_with_options(blame_opt_usage, options);
- }
- ctx.argv += n;
- ctx.argc -= n;
+ parse_revision_opt(&revs, &ctx, options, blame_opt_usage);
}
parse_done:
argc = parse_options_end(&ctx);
- seen_dashdash = 0;
- for (unk = i = 1; i < argc; i++) {
- const char *arg = argv[i];
- if (*arg != '-')
- break;
- else if (!strcmp("--", arg)) {
- seen_dashdash = 1;
- i++;
- break;
- }
- else
- argv[unk++] = arg;
- }
+ if (cmd_is_annotate)
+ output_option |= OUTPUT_ANNOTATE_COMPAT;
+
+ if (DIFF_OPT_TST(&revs.diffopt, FIND_COPIES_HARDER))
+ opt |= (PICKAXE_BLAME_COPY | PICKAXE_BLAME_MOVE |
+ PICKAXE_BLAME_COPY_HARDER);
if (!blame_move_score)
blame_move_score = BLAME_DEFAULT_MOVE_SCORE;
*
* The remaining are:
*
- * (1) if seen_dashdash, its either
- * "-options -- <path>" or
- * "-options -- <path> <rev>".
- * but the latter is allowed only if there is no
- * options that we passed to revision machinery.
+ * (1) if dashdash_pos != 0, its either
+ * "blame [revisions] -- <path>" or
+ * "blame -- <path> <rev>"
*
- * (2) otherwise, we may have "--" somewhere later and
- * might be looking at the first one of multiple 'rev'
- * parameters (e.g. " master ^next ^maint -- path").
- * See if there is a dashdash first, and give the
- * arguments before that to revision machinery.
- * After that there must be one 'path'.
+ * (2) otherwise, its one of the two:
+ * "blame [revisions] <path>"
+ * "blame <path> <rev>"
*
- * (3) otherwise, its one of the three:
- * "-options <path> <rev>"
- * "-options <rev> <path>"
- * "-options <path>"
- * but again the first one is allowed only if
- * there is no options that we passed to revision
- * machinery.
+ * Note that we must strip out <path> from the arguments: we do not
+ * want the path pruning but we may want "bottom" processing.
*/
-
- if (seen_dashdash) {
- /* (1) */
- if (argc <= i)
- usage_with_options(blame_opt_usage, options);
- path = add_prefix(prefix, argv[i]);
- if (i + 1 == argc - 1) {
- if (unk != 1)
+ if (dashdash_pos) {
+ switch (argc - dashdash_pos - 1) {
+ case 2: /* (1b) */
+ if (argc != 4)
usage_with_options(blame_opt_usage, options);
- argv[unk++] = argv[i + 1];
+ /* reorder for the new way: <rev> -- <path> */
+ argv[1] = argv[3];
+ argv[3] = argv[2];
+ argv[2] = "--";
+ /* FALLTHROUGH */
+ case 1: /* (1a) */
+ path = add_prefix(prefix, argv[--argc]);
+ argv[argc] = NULL;
+ break;
+ default:
+ usage_with_options(blame_opt_usage, options);
}
- else if (i + 1 != argc)
- /* garbage at end */
+ } else {
+ if (argc < 2)
usage_with_options(blame_opt_usage, options);
- }
- else {
- int j;
- for (j = i; !seen_dashdash && j < argc; j++)
- if (!strcmp(argv[j], "--"))
- seen_dashdash = j;
- if (seen_dashdash) {
- /* (2) */
- if (seen_dashdash + 1 != argc - 1)
- usage_with_options(blame_opt_usage, options);
- path = add_prefix(prefix, argv[seen_dashdash + 1]);
- for (j = i; j < seen_dashdash; j++)
- argv[unk++] = argv[j];
+ path = add_prefix(prefix, argv[argc - 1]);
+ if (argc == 3 && !has_string_in_work_tree(path)) { /* (2b) */
+ path = add_prefix(prefix, argv[1]);
+ argv[1] = argv[2];
}
- else {
- /* (3) */
- if (argc <= i)
- usage_with_options(blame_opt_usage, options);
- path = add_prefix(prefix, argv[i]);
- if (i + 1 == argc - 1) {
- final_commit_name = argv[i + 1];
-
- /* if (unk == 1) we could be getting
- * old-style
- */
- if (unk == 1 && !has_path_in_work_tree(path)) {
- path = add_prefix(prefix, argv[i + 1]);
- final_commit_name = argv[i];
- }
- }
- else if (i != argc - 1)
- usage_with_options(blame_opt_usage, options);
+ argv[argc - 1] = "--";
- setup_work_tree();
- if (!has_path_in_work_tree(path))
- die("cannot stat path %s: %s",
- path, strerror(errno));
- }
+ setup_work_tree();
+ if (!has_string_in_work_tree(path))
+ die("cannot stat path %s: %s", path, strerror(errno));
}
- if (final_commit_name)
- argv[unk++] = final_commit_name;
-
- /*
- * Now we got rev and path. We do not want the path pruning
- * but we may want "bottom" processing.
- */
- argv[unk++] = "--"; /* terminate the rev name */
- argv[unk] = NULL;
-
- setup_revisions(unk, argv, &revs, NULL);
+ setup_revisions(argc, argv, &revs, NULL);
memset(&sb, 0, sizeof(sb));
sb.revs = &revs;