git/builtin/blame.c

971 lines
26 KiB
C
Raw Normal View History

/*
* Blame
*
* Copyright (c) 2006, 2014 by its authors
* See COPYING for licensing conditions
*/
#include "cache.h"
#include "config.h"
#include "builtin.h"
#include "commit.h"
#include "diff.h"
#include "revision.h"
#include "quote.h"
#include "string-list.h"
#include "mailmap.h"
#include "parse-options.h"
#include "prio-queue.h"
#include "utf8.h"
#include "userdiff.h"
#include "line-range.h"
#include "line-log.h"
#include "dir.h"
#include "progress.h"
#include "object-store.h"
#include "blame.h"
static char blame_usage[] = N_("git blame [<options>] [<rev-opts>] [<rev>] [--] <file>");
static const char *blame_opt_usage[] = {
blame_usage,
"",
N_("<rev-opts> are documented in git-rev-list(1)"),
NULL
};
static int longest_file;
static int longest_author;
static int max_orig_digits;
static int max_digits;
static int max_score_digits;
static int show_root;
git-blame --reverse This new option allows "git blame" to read an old version of the file, and up to which commit each line survived (i.e. their children rewrote the line out of the contents). The previous revision machinery update to decorate each commit with its children was leading to this change. When the --reverse option is given, we read the old version and pass blame to the children of the current suspect, instead of the usual order of starting from the latest and passing blame to parents. The standard yardstick of "blame" in git.git history is "rev-list.c" which was refactored heavily in its existence. For example: git blame -C -C -w --reverse 9de48752..master -- rev-list.c begins like this: 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 1) #include "cache... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 2) #include "commi... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 3) #include "tree.... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 4) #include "blob.... 213523f4 rev-list.c (JC Hamano 2006-03-01 5) #include "epoch... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 6) ab57c8dd rev-list.c (JC Hamano 2006-02-24 7) #define SEEN ab57c8dd rev-list.c (JC Hamano 2006-02-24 8) #define INTERES... 213523f4 rev-list.c (JC Hamano 2006-03-01 9) #define COUNTED... 7e21c29b rev-list.c (LTorvalds 2005-07-06 10) #define SHOWN ... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 11) 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 12) static const ch... b1349229 rev-list.c (LTorvalds 2005-07-26 13) "usage: git-... This reveals that the original first four lines survived until now in builtin-rev-list.c , inclusion of "epoch.h" was removed after 213523f4 while the contents was still in rev-list.c. This mode probably needs more tweaking so that the commit that removed the line (i.e. the children of the commits listed in the above sample output) is shown instead to be useful, but then there is a little matter of which child of a fork point to show. For now, you can find the diff that rewrote the fifth line above by doing: $ git log --children 213523f4^.. to find its child, which is 1025fe5 (Merge branch 'lt/rev-list' into next, 2006-03-01), and then look at that child with: $ git show 1025fe5 Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-04-03 05:17:53 +00:00
static int reverse;
static int blank_boundary;
static int incremental;
static int xdl_opts;
static int abbrev = -1;
static int no_whole_file_rename;
static int show_progress;
convert "enum date_mode" into a struct In preparation for adding date modes that may carry extra information beyond the mode itself, this patch converts the date_mode enum into a struct. Most of the conversion is fairly straightforward; we pass the struct as a pointer and dereference the type field where necessary. Locations that declare a date_mode can use a "{}" constructor. However, the tricky case is where we use the enum labels as constants, like: show_date(t, tz, DATE_NORMAL); Ideally we could say: show_date(t, tz, &{ DATE_NORMAL }); but of course C does not allow that. Likewise, we cannot cast the constant to a struct, because we need to pass an actual address. Our options are basically: 1. Manually add a "struct date_mode d = { DATE_NORMAL }" definition to each caller, and pass "&d". This makes the callers uglier, because they sometimes do not even have their own scope (e.g., they are inside a switch statement). 2. Provide a pre-made global "date_normal" struct that can be passed by address. We'd also need "date_rfc2822", "date_iso8601", and so forth. But at least the ugliness is defined in one place. 3. Provide a wrapper that generates the correct struct on the fly. The big downside is that we end up pointing to a single global, which makes our wrapper non-reentrant. But show_date is already not reentrant, so it does not matter. This patch implements 3, along with a minor macro to keep the size of the callers sane. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-06-25 16:55:02 +00:00
static struct date_mode blame_date_mode = { DATE_ISO8601 };
static size_t blame_date_width;
static struct string_list mailmap = STRING_LIST_INIT_NODUP;
#ifndef DEBUG
#define DEBUG 0
#endif
static unsigned blame_move_score;
static unsigned blame_copy_score;
/* Remember to update object flag allocation in object.h */
#define METAINFO_SHOWN (1u<<12)
#define MORE_THAN_ONE_PATH (1u<<13)
struct progress_info {
struct progress *progress;
int blamed_lines;
};
static const char *nth_line_cb(void *data, long lno)
{
return blame_nth_line((struct blame_scoreboard *)data, lno);
}
/*
* Information on commits, used for output.
*/
struct commit_info {
struct strbuf author;
struct strbuf author_mail;
timestamp_t author_time;
struct strbuf author_tz;
/* filled only when asked for details */
struct strbuf committer;
struct strbuf committer_mail;
timestamp_t committer_time;
struct strbuf committer_tz;
struct strbuf summary;
};
/*
* Parse author/committer line in the commit object buffer
*/
static void get_ac_line(const char *inbuf, const char *what,
struct strbuf *name, struct strbuf *mail,
timestamp_t *time, struct strbuf *tz)
{
struct ident_split ident;
size_t len, maillen, namelen;
char *tmp, *endp;
const char *namebuf, *mailbuf;
tmp = strstr(inbuf, what);
if (!tmp)
goto error_out;
tmp += strlen(what);
endp = strchr(tmp, '\n');
if (!endp)
len = strlen(tmp);
else
len = endp - tmp;
if (split_ident_line(&ident, tmp, len)) {
error_out:
/* Ugh */
tmp = "(unknown)";
strbuf_addstr(name, tmp);
strbuf_addstr(mail, tmp);
strbuf_addstr(tz, tmp);
*time = 0;
return;
}
namelen = ident.name_end - ident.name_begin;
namebuf = ident.name_begin;
maillen = ident.mail_end - ident.mail_begin;
mailbuf = ident.mail_begin;
if (ident.date_begin && ident.date_end)
*time = strtoul(ident.date_begin, NULL, 10);
else
*time = 0;
if (ident.tz_begin && ident.tz_end)
strbuf_add(tz, ident.tz_begin, ident.tz_end - ident.tz_begin);
else
strbuf_addstr(tz, "(unknown)");
/*
* Now, convert both name and e-mail using mailmap
*/
map_user(&mailmap, &mailbuf, &maillen,
&namebuf, &namelen);
strbuf_addf(mail, "<%.*s>", (int)maillen, mailbuf);
strbuf_add(name, namebuf, namelen);
}
static void commit_info_init(struct commit_info *ci)
{
strbuf_init(&ci->author, 0);
strbuf_init(&ci->author_mail, 0);
strbuf_init(&ci->author_tz, 0);
strbuf_init(&ci->committer, 0);
strbuf_init(&ci->committer_mail, 0);
strbuf_init(&ci->committer_tz, 0);
strbuf_init(&ci->summary, 0);
}
static void commit_info_destroy(struct commit_info *ci)
{
strbuf_release(&ci->author);
strbuf_release(&ci->author_mail);
strbuf_release(&ci->author_tz);
strbuf_release(&ci->committer);
strbuf_release(&ci->committer_mail);
strbuf_release(&ci->committer_tz);
strbuf_release(&ci->summary);
}
static void get_commit_info(struct commit *commit,
struct commit_info *ret,
int detailed)
{
int len;
const char *subject, *encoding;
const char *message;
commit_info_init(ret);
encoding = get_log_output_encoding();
message = logmsg_reencode(commit, NULL, encoding);
get_ac_line(message, "\nauthor ",
&ret->author, &ret->author_mail,
&ret->author_time, &ret->author_tz);
if (!detailed) {
unuse_commit_buffer(commit, message);
return;
}
get_ac_line(message, "\ncommitter ",
&ret->committer, &ret->committer_mail,
&ret->committer_time, &ret->committer_tz);
len = find_commit_subject(message, &subject);
if (len)
strbuf_add(&ret->summary, subject, len);
else
strbuf_addf(&ret->summary, "(%s)", oid_to_hex(&commit->object.oid));
unuse_commit_buffer(commit, message);
}
/*
blame: output porcelain "previous" header for each file It's possible for content currently found in one file to have originated in two separate files, each of which may have been modified in some single older commit. The --porcelain output generates an incorrect "previous" header in this case, whereas --line-porcelain gets it right. The problem is that the porcelain output tries to omit repeated details of commits, and treats "previous" as a property of the commit, when it is really a property of the blamed block of lines. Let's look at an example. In a case like this, you might see this output from --line-porcelain: SOME_SHA1 1 1 1 author ... committer ... previous SOME_SHA1^ file_one filename file_one ...some line content... SOME_SHA1 2 1 1 author ... committer ... previous SOME_SHA1^ file_two filename file_two ...some different content.... The "filename" fields tell us that the two lines are from two different files. But notice that the filename also appears in the "previous" field, which tells us where to start a re-blame. The second content line never appeared in file_one at all, so we would obviously need to re-blame from file_two (or possibly even some other file, if had just been renamed to file_two in SOME_SHA1). So far so good. Now here's what --porcelain looks like: SOME_SHA1 1 1 1 author ... committer ... previous SOME_SHA1^ file_one filename file_one ...some line content... SOME_SHA1 2 1 1 filename file_two ...some different content.... We've dropped the author and committer fields from the second line, as they would just be repeats. But we can't omit "filename", because it depends on the actual block of blamed lines, not just the commit. This is handled by emit_porcelain_details(), which will show the filename either if it is the first mention of the commit _or_ if the commit has multiple paths in it. But we don't give "previous" the same handling. It's written inside emit_one_suspect_detail(), which bails early if we've already seen that commit. And so the output above is wrong; a reader would assume that the correct place to re-blame line two is from file_one, but that's obviously nonsense. Let's treat "previous" the same as "filename", and show it fresh whenever we know we are in a confusing case like this. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-01-06 04:20:51 +00:00
* Write out any suspect information which depends on the path. This must be
* handled separately from emit_one_suspect_detail(), because a given commit
* may have changes in multiple paths. So this needs to appear each time
* we mention a new group.
*
* To allow LF and other nonportable characters in pathnames,
* they are c-style quoted as needed.
*/
static void write_filename_info(struct blame_origin *suspect)
{
blame: output porcelain "previous" header for each file It's possible for content currently found in one file to have originated in two separate files, each of which may have been modified in some single older commit. The --porcelain output generates an incorrect "previous" header in this case, whereas --line-porcelain gets it right. The problem is that the porcelain output tries to omit repeated details of commits, and treats "previous" as a property of the commit, when it is really a property of the blamed block of lines. Let's look at an example. In a case like this, you might see this output from --line-porcelain: SOME_SHA1 1 1 1 author ... committer ... previous SOME_SHA1^ file_one filename file_one ...some line content... SOME_SHA1 2 1 1 author ... committer ... previous SOME_SHA1^ file_two filename file_two ...some different content.... The "filename" fields tell us that the two lines are from two different files. But notice that the filename also appears in the "previous" field, which tells us where to start a re-blame. The second content line never appeared in file_one at all, so we would obviously need to re-blame from file_two (or possibly even some other file, if had just been renamed to file_two in SOME_SHA1). So far so good. Now here's what --porcelain looks like: SOME_SHA1 1 1 1 author ... committer ... previous SOME_SHA1^ file_one filename file_one ...some line content... SOME_SHA1 2 1 1 filename file_two ...some different content.... We've dropped the author and committer fields from the second line, as they would just be repeats. But we can't omit "filename", because it depends on the actual block of blamed lines, not just the commit. This is handled by emit_porcelain_details(), which will show the filename either if it is the first mention of the commit _or_ if the commit has multiple paths in it. But we don't give "previous" the same handling. It's written inside emit_one_suspect_detail(), which bails early if we've already seen that commit. And so the output above is wrong; a reader would assume that the correct place to re-blame line two is from file_one, but that's obviously nonsense. Let's treat "previous" the same as "filename", and show it fresh whenever we know we are in a confusing case like this. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-01-06 04:20:51 +00:00
if (suspect->previous) {
struct blame_origin *prev = suspect->previous;
blame: output porcelain "previous" header for each file It's possible for content currently found in one file to have originated in two separate files, each of which may have been modified in some single older commit. The --porcelain output generates an incorrect "previous" header in this case, whereas --line-porcelain gets it right. The problem is that the porcelain output tries to omit repeated details of commits, and treats "previous" as a property of the commit, when it is really a property of the blamed block of lines. Let's look at an example. In a case like this, you might see this output from --line-porcelain: SOME_SHA1 1 1 1 author ... committer ... previous SOME_SHA1^ file_one filename file_one ...some line content... SOME_SHA1 2 1 1 author ... committer ... previous SOME_SHA1^ file_two filename file_two ...some different content.... The "filename" fields tell us that the two lines are from two different files. But notice that the filename also appears in the "previous" field, which tells us where to start a re-blame. The second content line never appeared in file_one at all, so we would obviously need to re-blame from file_two (or possibly even some other file, if had just been renamed to file_two in SOME_SHA1). So far so good. Now here's what --porcelain looks like: SOME_SHA1 1 1 1 author ... committer ... previous SOME_SHA1^ file_one filename file_one ...some line content... SOME_SHA1 2 1 1 filename file_two ...some different content.... We've dropped the author and committer fields from the second line, as they would just be repeats. But we can't omit "filename", because it depends on the actual block of blamed lines, not just the commit. This is handled by emit_porcelain_details(), which will show the filename either if it is the first mention of the commit _or_ if the commit has multiple paths in it. But we don't give "previous" the same handling. It's written inside emit_one_suspect_detail(), which bails early if we've already seen that commit. And so the output above is wrong; a reader would assume that the correct place to re-blame line two is from file_one, but that's obviously nonsense. Let's treat "previous" the same as "filename", and show it fresh whenever we know we are in a confusing case like this. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-01-06 04:20:51 +00:00
printf("previous %s ", oid_to_hex(&prev->commit->object.oid));
write_name_quoted(prev->path, stdout, '\n');
}
printf("filename ");
blame: output porcelain "previous" header for each file It's possible for content currently found in one file to have originated in two separate files, each of which may have been modified in some single older commit. The --porcelain output generates an incorrect "previous" header in this case, whereas --line-porcelain gets it right. The problem is that the porcelain output tries to omit repeated details of commits, and treats "previous" as a property of the commit, when it is really a property of the blamed block of lines. Let's look at an example. In a case like this, you might see this output from --line-porcelain: SOME_SHA1 1 1 1 author ... committer ... previous SOME_SHA1^ file_one filename file_one ...some line content... SOME_SHA1 2 1 1 author ... committer ... previous SOME_SHA1^ file_two filename file_two ...some different content.... The "filename" fields tell us that the two lines are from two different files. But notice that the filename also appears in the "previous" field, which tells us where to start a re-blame. The second content line never appeared in file_one at all, so we would obviously need to re-blame from file_two (or possibly even some other file, if had just been renamed to file_two in SOME_SHA1). So far so good. Now here's what --porcelain looks like: SOME_SHA1 1 1 1 author ... committer ... previous SOME_SHA1^ file_one filename file_one ...some line content... SOME_SHA1 2 1 1 filename file_two ...some different content.... We've dropped the author and committer fields from the second line, as they would just be repeats. But we can't omit "filename", because it depends on the actual block of blamed lines, not just the commit. This is handled by emit_porcelain_details(), which will show the filename either if it is the first mention of the commit _or_ if the commit has multiple paths in it. But we don't give "previous" the same handling. It's written inside emit_one_suspect_detail(), which bails early if we've already seen that commit. And so the output above is wrong; a reader would assume that the correct place to re-blame line two is from file_one, but that's obviously nonsense. Let's treat "previous" the same as "filename", and show it fresh whenever we know we are in a confusing case like this. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-01-06 04:20:51 +00:00
write_name_quoted(suspect->path, stdout, '\n');
}
/*
* Porcelain/Incremental format wants to show a lot of details per
* commit. Instead of repeating this every line, emit it only once,
* the first time each commit appears in the output (unless the
* user has specifically asked for us to repeat).
*/
static int emit_one_suspect_detail(struct blame_origin *suspect, int repeat)
{
struct commit_info ci;
if (!repeat && (suspect->commit->object.flags & METAINFO_SHOWN))
return 0;
suspect->commit->object.flags |= METAINFO_SHOWN;
get_commit_info(suspect->commit, &ci, 1);
printf("author %s\n", ci.author.buf);
printf("author-mail %s\n", ci.author_mail.buf);
printf("author-time %"PRItime"\n", ci.author_time);
printf("author-tz %s\n", ci.author_tz.buf);
printf("committer %s\n", ci.committer.buf);
printf("committer-mail %s\n", ci.committer_mail.buf);
printf("committer-time %"PRItime"\n", ci.committer_time);
printf("committer-tz %s\n", ci.committer_tz.buf);
printf("summary %s\n", ci.summary.buf);
if (suspect->commit->object.flags & UNINTERESTING)
printf("boundary\n");
commit_info_destroy(&ci);
return 1;
}
/*
* The blame_entry is found to be guilty for the range.
* Show it in incremental output.
*/
static void found_guilty_entry(struct blame_entry *ent, void *data)
{
struct progress_info *pi = (struct progress_info *)data;
if (incremental) {
struct blame_origin *suspect = ent->suspect;
printf("%s %d %d %d\n",
oid_to_hex(&suspect->commit->object.oid),
ent->s_lno + 1, ent->lno + 1, ent->num_lines);
emit_one_suspect_detail(suspect, 0);
blame: output porcelain "previous" header for each file It's possible for content currently found in one file to have originated in two separate files, each of which may have been modified in some single older commit. The --porcelain output generates an incorrect "previous" header in this case, whereas --line-porcelain gets it right. The problem is that the porcelain output tries to omit repeated details of commits, and treats "previous" as a property of the commit, when it is really a property of the blamed block of lines. Let's look at an example. In a case like this, you might see this output from --line-porcelain: SOME_SHA1 1 1 1 author ... committer ... previous SOME_SHA1^ file_one filename file_one ...some line content... SOME_SHA1 2 1 1 author ... committer ... previous SOME_SHA1^ file_two filename file_two ...some different content.... The "filename" fields tell us that the two lines are from two different files. But notice that the filename also appears in the "previous" field, which tells us where to start a re-blame. The second content line never appeared in file_one at all, so we would obviously need to re-blame from file_two (or possibly even some other file, if had just been renamed to file_two in SOME_SHA1). So far so good. Now here's what --porcelain looks like: SOME_SHA1 1 1 1 author ... committer ... previous SOME_SHA1^ file_one filename file_one ...some line content... SOME_SHA1 2 1 1 filename file_two ...some different content.... We've dropped the author and committer fields from the second line, as they would just be repeats. But we can't omit "filename", because it depends on the actual block of blamed lines, not just the commit. This is handled by emit_porcelain_details(), which will show the filename either if it is the first mention of the commit _or_ if the commit has multiple paths in it. But we don't give "previous" the same handling. It's written inside emit_one_suspect_detail(), which bails early if we've already seen that commit. And so the output above is wrong; a reader would assume that the correct place to re-blame line two is from file_one, but that's obviously nonsense. Let's treat "previous" the same as "filename", and show it fresh whenever we know we are in a confusing case like this. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-01-06 04:20:51 +00:00
write_filename_info(suspect);
maybe_flush_or_die(stdout, "stdout");
}
pi->blamed_lines += ent->num_lines;
display_progress(pi->progress, pi->blamed_lines);
}
static const char *format_time(timestamp_t time, const char *tz_str,
int show_raw_time)
{
static struct strbuf time_buf = STRBUF_INIT;
strbuf_reset(&time_buf);
if (show_raw_time) {
strbuf_addf(&time_buf, "%"PRItime" %s", time, tz_str);
}
else {
const char *time_str;
size_t time_width;
int tz;
tz = atoi(tz_str);
convert "enum date_mode" into a struct In preparation for adding date modes that may carry extra information beyond the mode itself, this patch converts the date_mode enum into a struct. Most of the conversion is fairly straightforward; we pass the struct as a pointer and dereference the type field where necessary. Locations that declare a date_mode can use a "{}" constructor. However, the tricky case is where we use the enum labels as constants, like: show_date(t, tz, DATE_NORMAL); Ideally we could say: show_date(t, tz, &{ DATE_NORMAL }); but of course C does not allow that. Likewise, we cannot cast the constant to a struct, because we need to pass an actual address. Our options are basically: 1. Manually add a "struct date_mode d = { DATE_NORMAL }" definition to each caller, and pass "&d". This makes the callers uglier, because they sometimes do not even have their own scope (e.g., they are inside a switch statement). 2. Provide a pre-made global "date_normal" struct that can be passed by address. We'd also need "date_rfc2822", "date_iso8601", and so forth. But at least the ugliness is defined in one place. 3. Provide a wrapper that generates the correct struct on the fly. The big downside is that we end up pointing to a single global, which makes our wrapper non-reentrant. But show_date is already not reentrant, so it does not matter. This patch implements 3, along with a minor macro to keep the size of the callers sane. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-06-25 16:55:02 +00:00
time_str = show_date(time, tz, &blame_date_mode);
strbuf_addstr(&time_buf, time_str);
/*
* Add space paddings to time_buf to display a fixed width
* string, and use time_width for display width calibration.
*/
for (time_width = utf8_strwidth(time_str);
time_width < blame_date_width;
time_width++)
strbuf_addch(&time_buf, ' ');
}
return time_buf.buf;
}
#define OUTPUT_ANNOTATE_COMPAT 001
#define OUTPUT_LONG_OBJECT_NAME 002
#define OUTPUT_RAW_TIMESTAMP 004
#define OUTPUT_PORCELAIN 010
#define OUTPUT_SHOW_NAME 020
#define OUTPUT_SHOW_NUMBER 040
#define OUTPUT_SHOW_SCORE 0100
#define OUTPUT_NO_AUTHOR 0200
#define OUTPUT_SHOW_EMAIL 0400
#define OUTPUT_LINE_PORCELAIN 01000
static void emit_porcelain_details(struct blame_origin *suspect, int repeat)
{
if (emit_one_suspect_detail(suspect, repeat) ||
(suspect->commit->object.flags & MORE_THAN_ONE_PATH))
blame: output porcelain "previous" header for each file It's possible for content currently found in one file to have originated in two separate files, each of which may have been modified in some single older commit. The --porcelain output generates an incorrect "previous" header in this case, whereas --line-porcelain gets it right. The problem is that the porcelain output tries to omit repeated details of commits, and treats "previous" as a property of the commit, when it is really a property of the blamed block of lines. Let's look at an example. In a case like this, you might see this output from --line-porcelain: SOME_SHA1 1 1 1 author ... committer ... previous SOME_SHA1^ file_one filename file_one ...some line content... SOME_SHA1 2 1 1 author ... committer ... previous SOME_SHA1^ file_two filename file_two ...some different content.... The "filename" fields tell us that the two lines are from two different files. But notice that the filename also appears in the "previous" field, which tells us where to start a re-blame. The second content line never appeared in file_one at all, so we would obviously need to re-blame from file_two (or possibly even some other file, if had just been renamed to file_two in SOME_SHA1). So far so good. Now here's what --porcelain looks like: SOME_SHA1 1 1 1 author ... committer ... previous SOME_SHA1^ file_one filename file_one ...some line content... SOME_SHA1 2 1 1 filename file_two ...some different content.... We've dropped the author and committer fields from the second line, as they would just be repeats. But we can't omit "filename", because it depends on the actual block of blamed lines, not just the commit. This is handled by emit_porcelain_details(), which will show the filename either if it is the first mention of the commit _or_ if the commit has multiple paths in it. But we don't give "previous" the same handling. It's written inside emit_one_suspect_detail(), which bails early if we've already seen that commit. And so the output above is wrong; a reader would assume that the correct place to re-blame line two is from file_one, but that's obviously nonsense. Let's treat "previous" the same as "filename", and show it fresh whenever we know we are in a confusing case like this. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-01-06 04:20:51 +00:00
write_filename_info(suspect);
}
static void emit_porcelain(struct blame_scoreboard *sb, struct blame_entry *ent,
int opt)
{
int repeat = opt & OUTPUT_LINE_PORCELAIN;
int cnt;
const char *cp;
struct blame_origin *suspect = ent->suspect;
char hex[GIT_MAX_HEXSZ + 1];
oid_to_hex_r(hex, &suspect->commit->object.oid);
printf("%s %d %d %d\n",
hex,
ent->s_lno + 1,
ent->lno + 1,
ent->num_lines);
emit_porcelain_details(suspect, repeat);
cp = blame_nth_line(sb, ent->lno);
for (cnt = 0; cnt < ent->num_lines; cnt++) {
char ch;
if (cnt) {
printf("%s %d %d\n", hex,
ent->s_lno + 1 + cnt,
ent->lno + 1 + cnt);
if (repeat)
emit_porcelain_details(suspect, 1);
}
putchar('\t');
do {
ch = *cp++;
putchar(ch);
} while (ch != '\n' &&
cp < sb->final_buf + sb->final_buf_size);
}
if (sb->final_buf_size && cp[-1] != '\n')
putchar('\n');
}
static void emit_other(struct blame_scoreboard *sb, struct blame_entry *ent, int opt)
{
int cnt;
const char *cp;
struct blame_origin *suspect = ent->suspect;
struct commit_info ci;
char hex[GIT_MAX_HEXSZ + 1];
int show_raw_time = !!(opt & OUTPUT_RAW_TIMESTAMP);
get_commit_info(suspect->commit, &ci, 1);
oid_to_hex_r(hex, &suspect->commit->object.oid);
cp = blame_nth_line(sb, ent->lno);
for (cnt = 0; cnt < ent->num_lines; cnt++) {
char ch;
int length = (opt & OUTPUT_LONG_OBJECT_NAME) ? GIT_SHA1_HEXSZ : abbrev;
if (suspect->commit->object.flags & UNINTERESTING) {
if (blank_boundary)
memset(hex, ' ', length);
else if (!(opt & OUTPUT_ANNOTATE_COMPAT)) {
length--;
putchar('^');
}
}
printf("%.*s", length, hex);
if (opt & OUTPUT_ANNOTATE_COMPAT) {
const char *name;
if (opt & OUTPUT_SHOW_EMAIL)
name = ci.author_mail.buf;
else
name = ci.author.buf;
printf("\t(%10s\t%10s\t%d)", name,
format_time(ci.author_time, ci.author_tz.buf,
show_raw_time),
ent->lno + 1 + cnt);
} else {
if (opt & OUTPUT_SHOW_SCORE)
printf(" %*d %02d",
max_score_digits, ent->score,
ent->suspect->refcnt);
if (opt & OUTPUT_SHOW_NAME)
printf(" %-*.*s", longest_file, longest_file,
suspect->path);
if (opt & OUTPUT_SHOW_NUMBER)
printf(" %*d", max_orig_digits,
ent->s_lno + 1 + cnt);
if (!(opt & OUTPUT_NO_AUTHOR)) {
const char *name;
int pad;
if (opt & OUTPUT_SHOW_EMAIL)
name = ci.author_mail.buf;
else
name = ci.author.buf;
pad = longest_author - utf8_strwidth(name);
printf(" (%s%*s %10s",
name, pad, "",
format_time(ci.author_time,
ci.author_tz.buf,
show_raw_time));
}
printf(" %*d) ",
max_digits, ent->lno + 1 + cnt);
}
do {
ch = *cp++;
putchar(ch);
} while (ch != '\n' &&
cp < sb->final_buf + sb->final_buf_size);
}
if (sb->final_buf_size && cp[-1] != '\n')
putchar('\n');
commit_info_destroy(&ci);
}
static void output(struct blame_scoreboard *sb, int option)
{
struct blame_entry *ent;
if (option & OUTPUT_PORCELAIN) {
for (ent = sb->ent; ent; ent = ent->next) {
int count = 0;
struct blame_origin *suspect;
struct commit *commit = ent->suspect->commit;
if (commit->object.flags & MORE_THAN_ONE_PATH)
continue;
for (suspect = commit->util; suspect; suspect = suspect->next) {
if (suspect->guilty && count++) {
commit->object.flags |= MORE_THAN_ONE_PATH;
break;
}
}
}
}
for (ent = sb->ent; ent; ent = ent->next) {
if (option & OUTPUT_PORCELAIN)
emit_porcelain(sb, ent, option);
else {
emit_other(sb, ent, option);
}
}
}
/*
* Add phony grafts for use with -S; this is primarily to
* support git's cvsserver that wants to give a linear history
* to its clients.
*/
static int read_ancestry(const char *graft_file)
{
FILE *fp = fopen_or_warn(graft_file, "r");
struct strbuf buf = STRBUF_INIT;
if (!fp)
return -1;
while (!strbuf_getwholeline(&buf, fp, '\n')) {
/* The format is just "Commit Parent1 Parent2 ...\n" */
struct commit_graft *graft = read_graft_line(&buf);
if (graft)
register_commit_graft(graft, 0);
}
fclose(fp);
strbuf_release(&buf);
return 0;
}
static int update_auto_abbrev(int auto_abbrev, struct blame_origin *suspect)
{
const char *uniq = find_unique_abbrev(&suspect->commit->object.oid,
auto_abbrev);
int len = strlen(uniq);
if (auto_abbrev < len)
return len;
return auto_abbrev;
}
/*
* How many columns do we need to show line numbers, authors,
* and filenames?
*/
static void find_alignment(struct blame_scoreboard *sb, int *option)
{
int longest_src_lines = 0;
int longest_dst_lines = 0;
unsigned largest_score = 0;
struct blame_entry *e;
int compute_auto_abbrev = (abbrev < 0);
int auto_abbrev = DEFAULT_ABBREV;
for (e = sb->ent; e; e = e->next) {
struct blame_origin *suspect = e->suspect;
int num;
if (compute_auto_abbrev)
auto_abbrev = update_auto_abbrev(auto_abbrev, suspect);
if (strcmp(suspect->path, sb->path))
*option |= OUTPUT_SHOW_NAME;
num = strlen(suspect->path);
if (longest_file < num)
longest_file = num;
if (!(suspect->commit->object.flags & METAINFO_SHOWN)) {
struct commit_info ci;
suspect->commit->object.flags |= METAINFO_SHOWN;
get_commit_info(suspect->commit, &ci, 1);
if (*option & OUTPUT_SHOW_EMAIL)
num = utf8_strwidth(ci.author_mail.buf);
else
num = utf8_strwidth(ci.author.buf);
if (longest_author < num)
longest_author = num;
commit_info_destroy(&ci);
}
num = e->s_lno + e->num_lines;
if (longest_src_lines < num)
longest_src_lines = num;
num = e->lno + e->num_lines;
if (longest_dst_lines < num)
longest_dst_lines = num;
if (largest_score < blame_entry_score(sb, e))
largest_score = blame_entry_score(sb, e);
}
max_orig_digits = decimal_width(longest_src_lines);
max_digits = decimal_width(longest_dst_lines);
max_score_digits = decimal_width(largest_score);
if (compute_auto_abbrev)
/* one more abbrev length is needed for the boundary commit */
abbrev = auto_abbrev + 1;
}
static void sanity_check_on_fail(struct blame_scoreboard *sb, int baa)
{
int opt = OUTPUT_SHOW_SCORE | OUTPUT_SHOW_NUMBER | OUTPUT_SHOW_NAME;
find_alignment(sb, &opt);
output(sb, opt);
die("Baa %d!", baa);
}
static unsigned parse_score(const char *arg)
{
char *end;
unsigned long score = strtoul(arg, &end, 10);
if (*end)
return 0;
return score;
}
static const char *add_prefix(const char *prefix, const char *path)
{
return prefix_path(prefix, prefix ? strlen(prefix) : 0, path);
}
static int git_blame_config(const char *var, const char *value, void *cb)
{
if (!strcmp(var, "blame.showroot")) {
show_root = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "blame.blankboundary")) {
blank_boundary = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "blame.showemail")) {
int *output_option = cb;
if (git_config_bool(var, value))
*output_option |= OUTPUT_SHOW_EMAIL;
else
*output_option &= ~OUTPUT_SHOW_EMAIL;
return 0;
}
if (!strcmp(var, "blame.date")) {
if (!value)
return config_error_nonbool(var);
convert "enum date_mode" into a struct In preparation for adding date modes that may carry extra information beyond the mode itself, this patch converts the date_mode enum into a struct. Most of the conversion is fairly straightforward; we pass the struct as a pointer and dereference the type field where necessary. Locations that declare a date_mode can use a "{}" constructor. However, the tricky case is where we use the enum labels as constants, like: show_date(t, tz, DATE_NORMAL); Ideally we could say: show_date(t, tz, &{ DATE_NORMAL }); but of course C does not allow that. Likewise, we cannot cast the constant to a struct, because we need to pass an actual address. Our options are basically: 1. Manually add a "struct date_mode d = { DATE_NORMAL }" definition to each caller, and pass "&d". This makes the callers uglier, because they sometimes do not even have their own scope (e.g., they are inside a switch statement). 2. Provide a pre-made global "date_normal" struct that can be passed by address. We'd also need "date_rfc2822", "date_iso8601", and so forth. But at least the ugliness is defined in one place. 3. Provide a wrapper that generates the correct struct on the fly. The big downside is that we end up pointing to a single global, which makes our wrapper non-reentrant. But show_date is already not reentrant, so it does not matter. This patch implements 3, along with a minor macro to keep the size of the callers sane. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-06-25 16:55:02 +00:00
parse_date_format(value, &blame_date_mode);
return 0;
}
if (git_diff_heuristic_config(var, value, cb) < 0)
return -1;
drop odd return value semantics from userdiff_config When the userdiff_config function was introduced in be58e70 (diff: unify external diff and funcname parsing code, 2008-10-05), it used a return value convention unlike any other config callback. Like other callbacks, it used "-1" to signal error. But it returned "1" to indicate that it found something, and "0" otherwise; other callbacks simply returned "0" to indicate that no error occurred. This distinction was necessary at the time, because the userdiff namespace overlapped slightly with the color configuration namespace. So "diff.color.foo" could mean "the 'foo' slot of diff coloring" or "the 'foo' component of the "color" userdiff driver". Because the color-parsing code would die on an unknown color slot, we needed the userdiff code to indicate that it had matched the variable, letting us bypass the color-parsing code entirely. Later, in 8b8e862 (ignore unknown color configuration, 2009-12-12), the color-parsing code learned to silently ignore unknown slots. This means we no longer need to protect userdiff-matched variables from reaching the color-parsing code. We can therefore change the userdiff_config calling convention to a more normal one. This drops some code from each caller, which is nice. But more importantly, it reduces the cognitive load for readers who may wonder why userdiff_config is unlike every other config callback. There's no need to add a new test confirming that this works; t4020 already contains a test that sets diff.color.external. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-07 18:23:02 +00:00
if (userdiff_config(var, value) < 0)
return -1;
return git_default_config(var, value, cb);
}
static int blame_copy_callback(const struct option *option, const char *arg, int unset)
{
int *opt = option->value;
/*
* -C enables copy from removed files;
* -C -C enables copy from existing files, but only
* when blaming a new file;
* -C -C -C enables copy from existing files for
* everybody
*/
if (*opt & PICKAXE_BLAME_COPY_HARDER)
*opt |= PICKAXE_BLAME_COPY_HARDEST;
if (*opt & PICKAXE_BLAME_COPY)
*opt |= PICKAXE_BLAME_COPY_HARDER;
*opt |= PICKAXE_BLAME_COPY | PICKAXE_BLAME_MOVE;
if (arg)
blame_copy_score = parse_score(arg);
return 0;
}
static int blame_move_callback(const struct option *option, const char *arg, int unset)
{
int *opt = option->value;
*opt |= PICKAXE_BLAME_MOVE;
if (arg)
blame_move_score = parse_score(arg);
return 0;
}
blame: tighten command line parser The command line parser of "git blame" is prepared to take an ancient odd argument order "blame <path> <rev>" in addition to the usual "blame [<rev>] <path>". It has at least two negative ramifications: - In order to tell these two apart, it checks if the last command line argument names a path in the working tree, using file_exists(). However, "blame <rev> <path>" is a request to explain each and every line in the contents of <path> stored in revision <rev> and does not need to have a working tree version of the file. A check with file_exists() is simply wrong. - To coerce that mistaken file_exists() check to work, the code calls setup_work_tree() before doing so, because the path it has is relative to the top-level of the project tree. However, "blame <rev> <path>" MUST be usable even in a bare repository, and there is no reason for letting setup_work_tree() complain and die with "This operation must be run in a work tree". To correct the former, switch to check if the last token is a revision (and if so, parse arguments using "blame <path> <rev>" rule). Correct the latter by getting rid of setup_work_tree() and file_exists() check--the only case the call to this function matters is when we are running "blame <path>" (i.e. no starting revision and asking to blame the working tree file at <path>, digging through the HEAD revision), but there is a call in setup_scoreboard() just before it calls fake_working_tree_commit(). Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-02-05 23:12:11 +00:00
static int is_a_rev(const char *name)
{
struct object_id oid;
if (get_oid(name, &oid))
return 0;
return OBJ_NONE < oid_object_info(the_repository, &oid, NULL);
blame: tighten command line parser The command line parser of "git blame" is prepared to take an ancient odd argument order "blame <path> <rev>" in addition to the usual "blame [<rev>] <path>". It has at least two negative ramifications: - In order to tell these two apart, it checks if the last command line argument names a path in the working tree, using file_exists(). However, "blame <rev> <path>" is a request to explain each and every line in the contents of <path> stored in revision <rev> and does not need to have a working tree version of the file. A check with file_exists() is simply wrong. - To coerce that mistaken file_exists() check to work, the code calls setup_work_tree() before doing so, because the path it has is relative to the top-level of the project tree. However, "blame <rev> <path>" MUST be usable even in a bare repository, and there is no reason for letting setup_work_tree() complain and die with "This operation must be run in a work tree". To correct the former, switch to check if the last token is a revision (and if so, parse arguments using "blame <path> <rev>" rule). Correct the latter by getting rid of setup_work_tree() and file_exists() check--the only case the call to this function matters is when we are running "blame <path>" (i.e. no starting revision and asking to blame the working tree file at <path>, digging through the HEAD revision), but there is a call in setup_scoreboard() just before it calls fake_working_tree_commit(). Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-02-05 23:12:11 +00:00
}
int cmd_blame(int argc, const char **argv, const char *prefix)
{
struct rev_info revs;
const char *path;
struct blame_scoreboard sb;
struct blame_origin *o;
struct blame_entry *ent = NULL;
long dashdash_pos, lno;
struct progress_info pi = { NULL, 0 };
struct string_list range_list = STRING_LIST_INIT_NODUP;
int output_option = 0, opt = 0;
int show_stats = 0;
const char *revs_file = NULL;
const char *contents_from = NULL;
const struct option options[] = {
OPT_BOOL(0, "incremental", &incremental, N_("Show blame entries as we find them, incrementally")),
OPT_BOOL('b', NULL, &blank_boundary, N_("Show blank SHA-1 for boundary commits (Default: off)")),
OPT_BOOL(0, "root", &show_root, N_("Do not treat root commits as boundaries (Default: off)")),
OPT_BOOL(0, "show-stats", &show_stats, N_("Show work cost statistics")),
OPT_BOOL(0, "progress", &show_progress, N_("Force progress reporting")),
OPT_BIT(0, "score-debug", &output_option, N_("Show output score for blame entries"), OUTPUT_SHOW_SCORE),
OPT_BIT('f', "show-name", &output_option, N_("Show original filename (Default: auto)"), OUTPUT_SHOW_NAME),
OPT_BIT('n', "show-number", &output_option, N_("Show original linenumber (Default: off)"), OUTPUT_SHOW_NUMBER),
OPT_BIT('p', "porcelain", &output_option, N_("Show in a format designed for machine consumption"), OUTPUT_PORCELAIN),
OPT_BIT(0, "line-porcelain", &output_option, N_("Show porcelain format with per-line commit information"), OUTPUT_PORCELAIN|OUTPUT_LINE_PORCELAIN),
OPT_BIT('c', NULL, &output_option, N_("Use the same output mode as git-annotate (Default: off)"), OUTPUT_ANNOTATE_COMPAT),
OPT_BIT('t', NULL, &output_option, N_("Show raw timestamp (Default: off)"), OUTPUT_RAW_TIMESTAMP),
OPT_BIT('l', NULL, &output_option, N_("Show long commit SHA1 (Default: off)"), OUTPUT_LONG_OBJECT_NAME),
OPT_BIT('s', NULL, &output_option, N_("Suppress author name and timestamp (Default: off)"), OUTPUT_NO_AUTHOR),
OPT_BIT('e', "show-email", &output_option, N_("Show author email instead of name (Default: off)"), OUTPUT_SHOW_EMAIL),
OPT_BIT('w', NULL, &xdl_opts, N_("Ignore whitespace differences"), XDF_IGNORE_WHITESPACE),
/*
* The following two options are parsed by parse_revision_opt()
* and are only included here to get included in the "-h"
* output:
*/
{ OPTION_LOWLEVEL_CALLBACK, 0, "indent-heuristic", NULL, NULL, N_("Use an experimental heuristic to improve diffs"), PARSE_OPT_NOARG, parse_opt_unknown_cb },
OPT_BIT(0, "minimal", &xdl_opts, N_("Spend extra cycles to find better match"), XDF_NEED_MINIMAL),
OPT_STRING('S', NULL, &revs_file, N_("file"), N_("Use revisions from <file> instead of calling git-rev-list")),
OPT_STRING(0, "contents", &contents_from, N_("file"), N_("Use <file>'s contents as the final image")),
{ OPTION_CALLBACK, 'C', NULL, &opt, N_("score"), N_("Find line copies within and across files"), PARSE_OPT_OPTARG, blame_copy_callback },
{ OPTION_CALLBACK, 'M', NULL, &opt, N_("score"), N_("Find line movements within and across files"), PARSE_OPT_OPTARG, blame_move_callback },
OPT_STRING_LIST('L', NULL, &range_list, N_("n,m"), N_("Process only line range n,m, counting from 1")),
OPT__ABBREV(&abbrev),
OPT_END()
};
struct parse_opt_ctx_t ctx;
int cmd_is_annotate = !strcmp(argv[0], "annotate");
struct range_set ranges;
unsigned int range_i;
long anchor;
git_config(git_blame_config, &output_option);
init_revisions(&revs, NULL);
revs.date_mode = blame_date_mode;
diff: make struct diff_flags members lowercase Now that the flags stored in struct diff_flags are being accessed directly and not through macros, change all struct members from being uppercase to lowercase. This conversion is done using the following semantic patch: @@ expression E; @@ - E.RECURSIVE + E.recursive @@ expression E; @@ - E.TREE_IN_RECURSIVE + E.tree_in_recursive @@ expression E; @@ - E.BINARY + E.binary @@ expression E; @@ - E.TEXT + E.text @@ expression E; @@ - E.FULL_INDEX + E.full_index @@ expression E; @@ - E.SILENT_ON_REMOVE + E.silent_on_remove @@ expression E; @@ - E.FIND_COPIES_HARDER + E.find_copies_harder @@ expression E; @@ - E.FOLLOW_RENAMES + E.follow_renames @@ expression E; @@ - E.RENAME_EMPTY + E.rename_empty @@ expression E; @@ - E.HAS_CHANGES + E.has_changes @@ expression E; @@ - E.QUICK + E.quick @@ expression E; @@ - E.NO_INDEX + E.no_index @@ expression E; @@ - E.ALLOW_EXTERNAL + E.allow_external @@ expression E; @@ - E.EXIT_WITH_STATUS + E.exit_with_status @@ expression E; @@ - E.REVERSE_DIFF + E.reverse_diff @@ expression E; @@ - E.CHECK_FAILED + E.check_failed @@ expression E; @@ - E.RELATIVE_NAME + E.relative_name @@ expression E; @@ - E.IGNORE_SUBMODULES + E.ignore_submodules @@ expression E; @@ - E.DIRSTAT_CUMULATIVE + E.dirstat_cumulative @@ expression E; @@ - E.DIRSTAT_BY_FILE + E.dirstat_by_file @@ expression E; @@ - E.ALLOW_TEXTCONV + E.allow_textconv @@ expression E; @@ - E.TEXTCONV_SET_VIA_CMDLINE + E.textconv_set_via_cmdline @@ expression E; @@ - E.DIFF_FROM_CONTENTS + E.diff_from_contents @@ expression E; @@ - E.DIRTY_SUBMODULES + E.dirty_submodules @@ expression E; @@ - E.IGNORE_UNTRACKED_IN_SUBMODULES + E.ignore_untracked_in_submodules @@ expression E; @@ - E.IGNORE_DIRTY_SUBMODULES + E.ignore_dirty_submodules @@ expression E; @@ - E.OVERRIDE_SUBMODULE_CONFIG + E.override_submodule_config @@ expression E; @@ - E.DIRSTAT_BY_LINE + E.dirstat_by_line @@ expression E; @@ - E.FUNCCONTEXT + E.funccontext @@ expression E; @@ - E.PICKAXE_IGNORE_CASE + E.pickaxe_ignore_case @@ expression E; @@ - E.DEFAULT_FOLLOW_RENAMES + E.default_follow_renames Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-31 18:19:11 +00:00
revs.diffopt.flags.allow_textconv = 1;
revs.diffopt.flags.follow_renames = 1;
save_commit_buffer = 0;
dashdash_pos = 0;
show_progress = -1;
parse_options_start(&ctx, argc, argv, prefix, options,
PARSE_OPT_KEEP_DASHDASH | PARSE_OPT_KEEP_ARGV0);
for (;;) {
switch (parse_options_step(&ctx, options, blame_opt_usage)) {
case PARSE_OPT_HELP:
case PARSE_OPT_ERROR:
exit(129);
case PARSE_OPT_DONE:
if (ctx.argv[0])
dashdash_pos = ctx.cpidx;
goto parse_done;
}
if (!strcmp(ctx.argv[0], "--reverse")) {
ctx.argv[0] = "--children";
reverse = 1;
}
parse_revision_opt(&revs, &ctx, options, blame_opt_usage);
}
parse_done:
diff: make struct diff_flags members lowercase Now that the flags stored in struct diff_flags are being accessed directly and not through macros, change all struct members from being uppercase to lowercase. This conversion is done using the following semantic patch: @@ expression E; @@ - E.RECURSIVE + E.recursive @@ expression E; @@ - E.TREE_IN_RECURSIVE + E.tree_in_recursive @@ expression E; @@ - E.BINARY + E.binary @@ expression E; @@ - E.TEXT + E.text @@ expression E; @@ - E.FULL_INDEX + E.full_index @@ expression E; @@ - E.SILENT_ON_REMOVE + E.silent_on_remove @@ expression E; @@ - E.FIND_COPIES_HARDER + E.find_copies_harder @@ expression E; @@ - E.FOLLOW_RENAMES + E.follow_renames @@ expression E; @@ - E.RENAME_EMPTY + E.rename_empty @@ expression E; @@ - E.HAS_CHANGES + E.has_changes @@ expression E; @@ - E.QUICK + E.quick @@ expression E; @@ - E.NO_INDEX + E.no_index @@ expression E; @@ - E.ALLOW_EXTERNAL + E.allow_external @@ expression E; @@ - E.EXIT_WITH_STATUS + E.exit_with_status @@ expression E; @@ - E.REVERSE_DIFF + E.reverse_diff @@ expression E; @@ - E.CHECK_FAILED + E.check_failed @@ expression E; @@ - E.RELATIVE_NAME + E.relative_name @@ expression E; @@ - E.IGNORE_SUBMODULES + E.ignore_submodules @@ expression E; @@ - E.DIRSTAT_CUMULATIVE + E.dirstat_cumulative @@ expression E; @@ - E.DIRSTAT_BY_FILE + E.dirstat_by_file @@ expression E; @@ - E.ALLOW_TEXTCONV + E.allow_textconv @@ expression E; @@ - E.TEXTCONV_SET_VIA_CMDLINE + E.textconv_set_via_cmdline @@ expression E; @@ - E.DIFF_FROM_CONTENTS + E.diff_from_contents @@ expression E; @@ - E.DIRTY_SUBMODULES + E.dirty_submodules @@ expression E; @@ - E.IGNORE_UNTRACKED_IN_SUBMODULES + E.ignore_untracked_in_submodules @@ expression E; @@ - E.IGNORE_DIRTY_SUBMODULES + E.ignore_dirty_submodules @@ expression E; @@ - E.OVERRIDE_SUBMODULE_CONFIG + E.override_submodule_config @@ expression E; @@ - E.DIRSTAT_BY_LINE + E.dirstat_by_line @@ expression E; @@ - E.FUNCCONTEXT + E.funccontext @@ expression E; @@ - E.PICKAXE_IGNORE_CASE + E.pickaxe_ignore_case @@ expression E; @@ - E.DEFAULT_FOLLOW_RENAMES + E.default_follow_renames Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-31 18:19:11 +00:00
no_whole_file_rename = !revs.diffopt.flags.follow_renames;
xdl_opts |= revs.diffopt.xdl_opts & XDF_INDENT_HEURISTIC;
diff: make struct diff_flags members lowercase Now that the flags stored in struct diff_flags are being accessed directly and not through macros, change all struct members from being uppercase to lowercase. This conversion is done using the following semantic patch: @@ expression E; @@ - E.RECURSIVE + E.recursive @@ expression E; @@ - E.TREE_IN_RECURSIVE + E.tree_in_recursive @@ expression E; @@ - E.BINARY + E.binary @@ expression E; @@ - E.TEXT + E.text @@ expression E; @@ - E.FULL_INDEX + E.full_index @@ expression E; @@ - E.SILENT_ON_REMOVE + E.silent_on_remove @@ expression E; @@ - E.FIND_COPIES_HARDER + E.find_copies_harder @@ expression E; @@ - E.FOLLOW_RENAMES + E.follow_renames @@ expression E; @@ - E.RENAME_EMPTY + E.rename_empty @@ expression E; @@ - E.HAS_CHANGES + E.has_changes @@ expression E; @@ - E.QUICK + E.quick @@ expression E; @@ - E.NO_INDEX + E.no_index @@ expression E; @@ - E.ALLOW_EXTERNAL + E.allow_external @@ expression E; @@ - E.EXIT_WITH_STATUS + E.exit_with_status @@ expression E; @@ - E.REVERSE_DIFF + E.reverse_diff @@ expression E; @@ - E.CHECK_FAILED + E.check_failed @@ expression E; @@ - E.RELATIVE_NAME + E.relative_name @@ expression E; @@ - E.IGNORE_SUBMODULES + E.ignore_submodules @@ expression E; @@ - E.DIRSTAT_CUMULATIVE + E.dirstat_cumulative @@ expression E; @@ - E.DIRSTAT_BY_FILE + E.dirstat_by_file @@ expression E; @@ - E.ALLOW_TEXTCONV + E.allow_textconv @@ expression E; @@ - E.TEXTCONV_SET_VIA_CMDLINE + E.textconv_set_via_cmdline @@ expression E; @@ - E.DIFF_FROM_CONTENTS + E.diff_from_contents @@ expression E; @@ - E.DIRTY_SUBMODULES + E.dirty_submodules @@ expression E; @@ - E.IGNORE_UNTRACKED_IN_SUBMODULES + E.ignore_untracked_in_submodules @@ expression E; @@ - E.IGNORE_DIRTY_SUBMODULES + E.ignore_dirty_submodules @@ expression E; @@ - E.OVERRIDE_SUBMODULE_CONFIG + E.override_submodule_config @@ expression E; @@ - E.DIRSTAT_BY_LINE + E.dirstat_by_line @@ expression E; @@ - E.FUNCCONTEXT + E.funccontext @@ expression E; @@ - E.PICKAXE_IGNORE_CASE + E.pickaxe_ignore_case @@ expression E; @@ - E.DEFAULT_FOLLOW_RENAMES + E.default_follow_renames Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-31 18:19:11 +00:00
revs.diffopt.flags.follow_renames = 0;
argc = parse_options_end(&ctx);
if (incremental || (output_option & OUTPUT_PORCELAIN)) {
if (show_progress > 0)
die(_("--progress can't be used with --incremental or porcelain formats"));
show_progress = 0;
} else if (show_progress < 0)
show_progress = isatty(2);
blame: fix alignment with --abbrev=40 The blame command internally adds 1 to any requested sha1 abbreviation length, and then subtracts it when outputting a boundary commit. This lets regular and boundary sha1s line up visually, but it misses one corner case. When the requested length is 40, we bump the value to 41. But since we only have 40 characters, that's all we can show (fortunately the truncation is done by a printf precision field, so it never tries to read past the end of the buffer). So a normal sha1 shows 40 hex characters, and a boundary sha1 shows "^" plus 40 hex characters. The result is misaligned. The "-l" option to show long sha1s gets around this by skipping the "abbrev" variable entirely and just always using GIT_SHA1_HEXSZ. This avoids the "+1" issue, but it does mean that boundary commits only have 39 characters printed. This is somewhat odd, but it does look good visually: the results are aligned and left-justified. The alternative would be to allocate an extra column that would contain either an extra space or the "^" boundary marker. As this is by definition the human-readable view, it's probably not that big a deal either way (and of course --porcelain, etc, correctly produce correct 40-hex sha1s). But for consistency, this patch teaches --abbrev=40 to produce the same output as "-l" (always left-aligned, with 40-hex for normal sha1s, and "^" plus 39-hex for boundaries). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-01-06 04:17:40 +00:00
if (0 < abbrev && abbrev < GIT_SHA1_HEXSZ)
/* one more abbrev length is needed for the boundary commit */
abbrev++;
else if (!abbrev)
abbrev = GIT_SHA1_HEXSZ;
if (revs_file && read_ancestry(revs_file))
die_errno("reading graft file '%s' failed", revs_file);
if (cmd_is_annotate) {
output_option |= OUTPUT_ANNOTATE_COMPAT;
convert "enum date_mode" into a struct In preparation for adding date modes that may carry extra information beyond the mode itself, this patch converts the date_mode enum into a struct. Most of the conversion is fairly straightforward; we pass the struct as a pointer and dereference the type field where necessary. Locations that declare a date_mode can use a "{}" constructor. However, the tricky case is where we use the enum labels as constants, like: show_date(t, tz, DATE_NORMAL); Ideally we could say: show_date(t, tz, &{ DATE_NORMAL }); but of course C does not allow that. Likewise, we cannot cast the constant to a struct, because we need to pass an actual address. Our options are basically: 1. Manually add a "struct date_mode d = { DATE_NORMAL }" definition to each caller, and pass "&d". This makes the callers uglier, because they sometimes do not even have their own scope (e.g., they are inside a switch statement). 2. Provide a pre-made global "date_normal" struct that can be passed by address. We'd also need "date_rfc2822", "date_iso8601", and so forth. But at least the ugliness is defined in one place. 3. Provide a wrapper that generates the correct struct on the fly. The big downside is that we end up pointing to a single global, which makes our wrapper non-reentrant. But show_date is already not reentrant, so it does not matter. This patch implements 3, along with a minor macro to keep the size of the callers sane. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-06-25 16:55:02 +00:00
blame_date_mode.type = DATE_ISO8601;
} else {
blame_date_mode = revs.date_mode;
}
/* The maximum width used to show the dates */
convert "enum date_mode" into a struct In preparation for adding date modes that may carry extra information beyond the mode itself, this patch converts the date_mode enum into a struct. Most of the conversion is fairly straightforward; we pass the struct as a pointer and dereference the type field where necessary. Locations that declare a date_mode can use a "{}" constructor. However, the tricky case is where we use the enum labels as constants, like: show_date(t, tz, DATE_NORMAL); Ideally we could say: show_date(t, tz, &{ DATE_NORMAL }); but of course C does not allow that. Likewise, we cannot cast the constant to a struct, because we need to pass an actual address. Our options are basically: 1. Manually add a "struct date_mode d = { DATE_NORMAL }" definition to each caller, and pass "&d". This makes the callers uglier, because they sometimes do not even have their own scope (e.g., they are inside a switch statement). 2. Provide a pre-made global "date_normal" struct that can be passed by address. We'd also need "date_rfc2822", "date_iso8601", and so forth. But at least the ugliness is defined in one place. 3. Provide a wrapper that generates the correct struct on the fly. The big downside is that we end up pointing to a single global, which makes our wrapper non-reentrant. But show_date is already not reentrant, so it does not matter. This patch implements 3, along with a minor macro to keep the size of the callers sane. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-06-25 16:55:02 +00:00
switch (blame_date_mode.type) {
case DATE_RFC2822:
blame_date_width = sizeof("Thu, 19 Oct 2006 16:00:04 -0700");
break;
case DATE_ISO8601_STRICT:
blame_date_width = sizeof("2006-10-19T16:00:04-07:00");
break;
case DATE_ISO8601:
blame_date_width = sizeof("2006-10-19 16:00:04 -0700");
break;
case DATE_RAW:
blame_date_width = sizeof("1161298804 -0700");
break;
case DATE_UNIX:
blame_date_width = sizeof("1161298804");
break;
case DATE_SHORT:
blame_date_width = sizeof("2006-10-19");
break;
case DATE_RELATIVE:
C style: use standard style for "TRANSLATORS" comments Change all the "TRANSLATORS: [...]" comments in the C code to use the regular Git coding style, and amend the style guide so that the example there uses that style. This custom style was necessary back in 2010 when the gettext support was initially added, and was subsequently documented in commit cbcfd4e3ea ("i18n: mention "TRANSLATORS:" marker in Documentation/CodingGuidelines", 2014-04-18). GNU xgettext hasn't had the parsing limitation that necessitated this exception for almost 3 years. Since its 0.19 release on 2014-06-02 it's been able to recognize TRANSLATOR comments in the standard Git comment syntax[1]. Usually we'd like to keep compatibility with software that's that young, but in this case literally the only person who needs to be using a gettext newer than 3 years old is Jiang Xin (the only person who runs & commits "make pot" results), so I think in this case we can make an exception. This xgettext parsing feature was added after a thread on the Git mailing list[2] which continued on the bug-gettext[3] list, but we never subsequently changed our style & styleguide, do so. There are already longstanding changes in git that use the standard comment style & have their TRANSLATORS comments extracted properly without getting the literal "*"'s mixed up in the text, as would happen before xgettext 0.19. Commit 7ff2683253 ("builtin-am: implement -i/--interactive", 2015-08-04) added one such comment, which in commit df0617bfa7 ("l10n: git.pot: v2.6.0 round 1 (123 new, 41 removed)", 2015-09-05) got picked up in the po/git.pot file with the right format, showing that Jiang already runs a modern xgettext. The xgettext parser does not handle the sort of non-standard comment style that I'm amending here in sequencer.c, but that isn't standard Git comment syntax anyway. With this change to sequencer.c & "make pot" the comment in the pot file is now correct: #. TRANSLATORS: %s will be "revert", "cherry-pick" or -#. * "rebase -i". +#. "rebase -i". 1. http://git.savannah.gnu.org/cgit/gettext.git/commit/?id=10af7fe6bd 2. <2ce9ec406501d112e032c8208417f8100bed04c6.1397712142.git.worldhello.net@gmail.com> (https://public-inbox.org/git/2ce9ec406501d112e032c8208417f8100bed04c6.1397712142.git.worldhello.net@gmail.com/) 3. https://lists.gnu.org/archive/html/bug-gettext/2014-04/msg00016.html Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Acked-by: Jiang Xin <worldhello.net@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-11 21:20:12 +00:00
/*
* TRANSLATORS: This string is used to tell us the
* maximum display width for a relative timestamp in
* "git blame" output. For C locale, "4 years, 11
* months ago", which takes 22 places, is the longest
* among various forms of relative timestamps, but
* your language may need more or fewer display
* columns.
*/
blame_date_width = utf8_strwidth(_("4 years, 11 months ago")) + 1; /* add the null */
break;
case DATE_NORMAL:
blame_date_width = sizeof("Thu Oct 19 16:00:04 2006 -0700");
break;
case DATE_STRFTIME:
blame_date_width = strlen(show_date(0, 0, &blame_date_mode)) + 1; /* add the null */
break;
}
blame_date_width -= 1; /* strip the null */
diff: make struct diff_flags members lowercase Now that the flags stored in struct diff_flags are being accessed directly and not through macros, change all struct members from being uppercase to lowercase. This conversion is done using the following semantic patch: @@ expression E; @@ - E.RECURSIVE + E.recursive @@ expression E; @@ - E.TREE_IN_RECURSIVE + E.tree_in_recursive @@ expression E; @@ - E.BINARY + E.binary @@ expression E; @@ - E.TEXT + E.text @@ expression E; @@ - E.FULL_INDEX + E.full_index @@ expression E; @@ - E.SILENT_ON_REMOVE + E.silent_on_remove @@ expression E; @@ - E.FIND_COPIES_HARDER + E.find_copies_harder @@ expression E; @@ - E.FOLLOW_RENAMES + E.follow_renames @@ expression E; @@ - E.RENAME_EMPTY + E.rename_empty @@ expression E; @@ - E.HAS_CHANGES + E.has_changes @@ expression E; @@ - E.QUICK + E.quick @@ expression E; @@ - E.NO_INDEX + E.no_index @@ expression E; @@ - E.ALLOW_EXTERNAL + E.allow_external @@ expression E; @@ - E.EXIT_WITH_STATUS + E.exit_with_status @@ expression E; @@ - E.REVERSE_DIFF + E.reverse_diff @@ expression E; @@ - E.CHECK_FAILED + E.check_failed @@ expression E; @@ - E.RELATIVE_NAME + E.relative_name @@ expression E; @@ - E.IGNORE_SUBMODULES + E.ignore_submodules @@ expression E; @@ - E.DIRSTAT_CUMULATIVE + E.dirstat_cumulative @@ expression E; @@ - E.DIRSTAT_BY_FILE + E.dirstat_by_file @@ expression E; @@ - E.ALLOW_TEXTCONV + E.allow_textconv @@ expression E; @@ - E.TEXTCONV_SET_VIA_CMDLINE + E.textconv_set_via_cmdline @@ expression E; @@ - E.DIFF_FROM_CONTENTS + E.diff_from_contents @@ expression E; @@ - E.DIRTY_SUBMODULES + E.dirty_submodules @@ expression E; @@ - E.IGNORE_UNTRACKED_IN_SUBMODULES + E.ignore_untracked_in_submodules @@ expression E; @@ - E.IGNORE_DIRTY_SUBMODULES + E.ignore_dirty_submodules @@ expression E; @@ - E.OVERRIDE_SUBMODULE_CONFIG + E.override_submodule_config @@ expression E; @@ - E.DIRSTAT_BY_LINE + E.dirstat_by_line @@ expression E; @@ - E.FUNCCONTEXT + E.funccontext @@ expression E; @@ - E.PICKAXE_IGNORE_CASE + E.pickaxe_ignore_case @@ expression E; @@ - E.DEFAULT_FOLLOW_RENAMES + E.default_follow_renames Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-31 18:19:11 +00:00
if (revs.diffopt.flags.find_copies_harder)
opt |= (PICKAXE_BLAME_COPY | PICKAXE_BLAME_MOVE |
PICKAXE_BLAME_COPY_HARDER);
/*
* We have collected options unknown to us in argv[1..unk]
* which are to be passed to revision machinery if we are
* going to do the "bottom" processing.
*
* The remaining are:
*
* (1) if dashdash_pos != 0, it is either
* "blame [revisions] -- <path>" or
* "blame -- <path> <rev>"
*
* (2) otherwise, it is one of the two:
* "blame [revisions] <path>"
* "blame <path> <rev>"
*
* Note that we must strip out <path> from the arguments: we do not
* want the path pruning but we may want "bottom" processing.
*/
if (dashdash_pos) {
switch (argc - dashdash_pos - 1) {
case 2: /* (1b) */
if (argc != 4)
usage_with_options(blame_opt_usage, options);
/* 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 (argc < 2)
usage_with_options(blame_opt_usage, options);
blame: tighten command line parser The command line parser of "git blame" is prepared to take an ancient odd argument order "blame <path> <rev>" in addition to the usual "blame [<rev>] <path>". It has at least two negative ramifications: - In order to tell these two apart, it checks if the last command line argument names a path in the working tree, using file_exists(). However, "blame <rev> <path>" is a request to explain each and every line in the contents of <path> stored in revision <rev> and does not need to have a working tree version of the file. A check with file_exists() is simply wrong. - To coerce that mistaken file_exists() check to work, the code calls setup_work_tree() before doing so, because the path it has is relative to the top-level of the project tree. However, "blame <rev> <path>" MUST be usable even in a bare repository, and there is no reason for letting setup_work_tree() complain and die with "This operation must be run in a work tree". To correct the former, switch to check if the last token is a revision (and if so, parse arguments using "blame <path> <rev>" rule). Correct the latter by getting rid of setup_work_tree() and file_exists() check--the only case the call to this function matters is when we are running "blame <path>" (i.e. no starting revision and asking to blame the working tree file at <path>, digging through the HEAD revision), but there is a call in setup_scoreboard() just before it calls fake_working_tree_commit(). Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-02-05 23:12:11 +00:00
if (argc == 3 && is_a_rev(argv[argc - 1])) { /* (2b) */
path = add_prefix(prefix, argv[1]);
argv[1] = argv[2];
blame: tighten command line parser The command line parser of "git blame" is prepared to take an ancient odd argument order "blame <path> <rev>" in addition to the usual "blame [<rev>] <path>". It has at least two negative ramifications: - In order to tell these two apart, it checks if the last command line argument names a path in the working tree, using file_exists(). However, "blame <rev> <path>" is a request to explain each and every line in the contents of <path> stored in revision <rev> and does not need to have a working tree version of the file. A check with file_exists() is simply wrong. - To coerce that mistaken file_exists() check to work, the code calls setup_work_tree() before doing so, because the path it has is relative to the top-level of the project tree. However, "blame <rev> <path>" MUST be usable even in a bare repository, and there is no reason for letting setup_work_tree() complain and die with "This operation must be run in a work tree". To correct the former, switch to check if the last token is a revision (and if so, parse arguments using "blame <path> <rev>" rule). Correct the latter by getting rid of setup_work_tree() and file_exists() check--the only case the call to this function matters is when we are running "blame <path>" (i.e. no starting revision and asking to blame the working tree file at <path>, digging through the HEAD revision), but there is a call in setup_scoreboard() just before it calls fake_working_tree_commit(). Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-02-05 23:12:11 +00:00
} else { /* (2a) */
if (argc == 2 && is_a_rev(argv[1]) && !get_git_work_tree())
die("missing <path> to blame");
path = add_prefix(prefix, argv[argc - 1]);
}
argv[argc - 1] = "--";
}
revs.disable_stdin = 1;
setup_revisions(argc, argv, &revs, NULL);
init_scoreboard(&sb);
git-blame --reverse This new option allows "git blame" to read an old version of the file, and up to which commit each line survived (i.e. their children rewrote the line out of the contents). The previous revision machinery update to decorate each commit with its children was leading to this change. When the --reverse option is given, we read the old version and pass blame to the children of the current suspect, instead of the usual order of starting from the latest and passing blame to parents. The standard yardstick of "blame" in git.git history is "rev-list.c" which was refactored heavily in its existence. For example: git blame -C -C -w --reverse 9de48752..master -- rev-list.c begins like this: 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 1) #include "cache... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 2) #include "commi... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 3) #include "tree.... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 4) #include "blob.... 213523f4 rev-list.c (JC Hamano 2006-03-01 5) #include "epoch... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 6) ab57c8dd rev-list.c (JC Hamano 2006-02-24 7) #define SEEN ab57c8dd rev-list.c (JC Hamano 2006-02-24 8) #define INTERES... 213523f4 rev-list.c (JC Hamano 2006-03-01 9) #define COUNTED... 7e21c29b rev-list.c (LTorvalds 2005-07-06 10) #define SHOWN ... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 11) 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 12) static const ch... b1349229 rev-list.c (LTorvalds 2005-07-26 13) "usage: git-... This reveals that the original first four lines survived until now in builtin-rev-list.c , inclusion of "epoch.h" was removed after 213523f4 while the contents was still in rev-list.c. This mode probably needs more tweaking so that the commit that removed the line (i.e. the children of the commits listed in the above sample output) is shown instead to be useful, but then there is a little matter of which child of a fork point to show. For now, you can find the diff that rewrote the fifth line above by doing: $ git log --children 213523f4^.. to find its child, which is 1025fe5 (Merge branch 'lt/rev-list' into next, 2006-03-01), and then look at that child with: $ git show 1025fe5 Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-04-03 05:17:53 +00:00
sb.revs = &revs;
sb.contents_from = contents_from;
sb.reverse = reverse;
setup_scoreboard(&sb, path, &o);
lno = sb.num_lines;
if (lno && !range_list.nr)
string_list_append(&range_list, "1");
anchor = 1;
range_set_init(&ranges, range_list.nr);
for (range_i = 0; range_i < range_list.nr; ++range_i) {
long bottom, top;
if (parse_range_arg(range_list.items[range_i].string,
nth_line_cb, &sb, lno, anchor,
&bottom, &top, sb.path))
usage(blame_usage);
if (lno < top || ((lno || bottom) && lno < bottom))
die(Q_("file %s has only %lu line",
"file %s has only %lu lines",
lno), path, lno);
if (bottom < 1)
bottom = 1;
if (top < 1)
top = lno;
bottom--;
range_set_append_unsafe(&ranges, bottom, top);
anchor = top + 1;
}
sort_and_merge_range_set(&ranges);
for (range_i = ranges.nr; range_i > 0; --range_i) {
const struct range *r = &ranges.ranges[range_i - 1];
ent = blame_entry_prepend(ent, r->start, r->end, o);
}
o->suspects = ent;
prio_queue_put(&sb.commits, o->commit);
blame_origin_decref(o);
range_set_release(&ranges);
string_list_clear(&range_list, 0);
sb.ent = NULL;
sb.path = path;
if (blame_move_score)
sb.move_score = blame_move_score;
if (blame_copy_score)
sb.copy_score = blame_copy_score;
sb.debug = DEBUG;
sb.on_sanity_fail = &sanity_check_on_fail;
sb.show_root = show_root;
sb.xdl_opts = xdl_opts;
sb.no_whole_file_rename = no_whole_file_rename;
read_mailmap(&mailmap, NULL);
sb.found_guilty_entry = &found_guilty_entry;
sb.found_guilty_entry_data = &pi;
if (show_progress)
progress: simplify "delayed" progress API We used to expose the full power of the delayed progress API to the callers, so that they can specify, not just the message to show and expected total amount of work that is used to compute the percentage of work performed so far, the percent-threshold parameter P and the delay-seconds parameter N. The progress meter starts to show at N seconds into the operation only if we have not yet completed P per-cent of the total work. Most callers used either (0%, 2s) or (50%, 1s) as (P, N), but there are oddballs that chose more random-looking values like 95%. For a smoother workload, (50%, 1s) would allow us to start showing the progress meter earlier than (0%, 2s), while keeping the chance of not showing progress meter for long running operation the same as the latter. For a task that would take 2s or more to complete, it is likely that less than half of it would complete within the first second, if the workload is smooth. But for a spiky workload whose earlier part is easier, such a setting is likely to fail to show the progress meter entirely and (0%, 2s) is more appropriate. But that is merely a theory. Realistically, it is of dubious value to ask each codepath to carefully consider smoothness of their workload and specify their own setting by passing two extra parameters. Let's simplify the API by dropping both parameters and have everybody use (0%, 2s). Oh, by the way, the percent-threshold parameter and the structure member were consistently misspelled, which also is now fixed ;-) Helped-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-08-19 17:39:41 +00:00
pi.progress = start_delayed_progress(_("Blaming lines"), sb.num_lines);
assign_blame(&sb, opt);
stop_progress(&pi.progress);
if (!incremental)
setup_pager();
else
return 0;
blame_sort_final(&sb);
blame_coalesce(&sb);
if (!(output_option & OUTPUT_PORCELAIN))
find_alignment(&sb, &output_option);
output(&sb, output_option);
free((void *)sb.final_buf);
for (ent = sb.ent; ent; ) {
struct blame_entry *e = ent->next;
free(ent);
ent = e;
}
if (show_stats) {
printf("num read blob: %d\n", sb.num_read_blob);
printf("num get patch: %d\n", sb.num_get_patch);
printf("num commits: %d\n", sb.num_commits);
}
return 0;
}