git/diff.c

3871 lines
100 KiB
C
Raw Normal View History

/*
* Copyright (C) 2005 Junio C Hamano
*/
#include "cache.h"
#include "quote.h"
#include "diff.h"
#include "diffcore.h"
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
#include "delta.h"
#include "xdiff-interface.h"
#include "color.h"
#include "attr.h"
#include "run-command.h"
#include "utf8.h"
#include "userdiff.h"
#include "sigchain.h"
#include "submodule.h"
Avoid accessing a slow working copy during diffcore operations. The Cygwin folks have done a fine job at creating a POSIX layer on Windows That Just Works(tm). However it comes with a penalty; accessing files in the working tree by way of stat/open/mmap can be slower for diffcore than inflating the data from a blob which is stored in a packfile. This performance problem is especially an issue in merge-recursive when dealing with nearly 7000 added files, as we are loading each file's content from the working directory to perform rename detection. I have literally seen (and sadly watched) paint dry in less time than it takes for merge-recursive to finish such a merge. On the other hand this very same merge runs very fast on Solaris. If Git is compiled with NO_FAST_WORKING_DIRECTORY set then we will avoid looking at the working directory when the blob in question is available within a packfile and the caller doesn't need the data unpacked into a temporary file. We don't use loose objects as they have the same open/mmap/close costs as the working directory file access, but have the additional CPU overhead of needing to inflate the content before use. So it is still faster to use the working tree file over the loose object. If the caller needs the file data unpacked into a temporary file its likely because they are going to call an external diff program, passing the file as a parameter. In this case reusing the working tree file will be faster as we don't need to inflate the data and write it out to a temporary file. The NO_FAST_WORKING_DIRECTORY feature is enabled by default on Cygwin, as that is the platform which currently appears to benefit the most from this option. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-12-14 19:15:57 +08:00
#ifdef NO_FAST_WORKING_DIRECTORY
#define FAST_WORKING_DIRECTORY 0
#else
#define FAST_WORKING_DIRECTORY 1
#endif
static int diff_detect_rename_default;
static int diff_rename_limit_default = 200;
static int diff_suppress_blank_empty;
int diff_use_color_default = -1;
static const char *diff_word_regex_cfg;
static const char *external_diff_cmd_cfg;
int diff_auto_refresh_index = 1;
static int diff_mnemonic_prefix;
static char diff_colors[][COLOR_MAXLEN] = {
GIT_COLOR_RESET,
GIT_COLOR_NORMAL, /* PLAIN */
GIT_COLOR_BOLD, /* METAINFO */
GIT_COLOR_CYAN, /* FRAGINFO */
GIT_COLOR_RED, /* OLD */
GIT_COLOR_GREEN, /* NEW */
GIT_COLOR_YELLOW, /* COMMIT */
GIT_COLOR_BG_RED, /* WHITESPACE */
GIT_COLOR_NORMAL, /* FUNCINFO */
};
static void diff_filespec_load_driver(struct diff_filespec *one);
static char *run_textconv(const char *, struct diff_filespec *, size_t *);
static int parse_diff_color_slot(const char *var, int ofs)
{
if (!strcasecmp(var+ofs, "plain"))
return DIFF_PLAIN;
if (!strcasecmp(var+ofs, "meta"))
return DIFF_METAINFO;
if (!strcasecmp(var+ofs, "frag"))
return DIFF_FRAGINFO;
if (!strcasecmp(var+ofs, "old"))
return DIFF_FILE_OLD;
if (!strcasecmp(var+ofs, "new"))
return DIFF_FILE_NEW;
if (!strcasecmp(var+ofs, "commit"))
return DIFF_COMMIT;
if (!strcasecmp(var+ofs, "whitespace"))
return DIFF_WHITESPACE;
if (!strcasecmp(var+ofs, "func"))
return DIFF_FUNCINFO;
2009-12-12 20:25:24 +08:00
return -1;
}
static int git_config_rename(const char *var, const char *value)
{
if (!value)
return DIFF_DETECT_RENAME;
if (!strcasecmp(value, "copies") || !strcasecmp(value, "copy"))
return DIFF_DETECT_COPY;
return git_config_bool(var,value) ? DIFF_DETECT_RENAME : 0;
}
/*
* These are to give UI layer defaults.
* The core-level commands such as git-diff-files should
* never be affected by the setting of diff.renames
* the user happens to have in the configuration file.
*/
int git_diff_ui_config(const char *var, const char *value, void *cb)
{
if (!strcmp(var, "diff.color") || !strcmp(var, "color.diff")) {
diff_use_color_default = git_config_colorbool(var, value, -1);
return 0;
}
if (!strcmp(var, "diff.renames")) {
diff_detect_rename_default = git_config_rename(var, value);
return 0;
}
if (!strcmp(var, "diff.autorefreshindex")) {
diff_auto_refresh_index = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "diff.mnemonicprefix")) {
diff_mnemonic_prefix = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "diff.external"))
return git_config_string(&external_diff_cmd_cfg, var, value);
if (!strcmp(var, "diff.wordregex"))
return git_config_string(&diff_word_regex_cfg, var, value);
return git_diff_basic_config(var, value, cb);
}
int git_diff_basic_config(const char *var, const char *value, void *cb)
{
if (!strcmp(var, "diff.renamelimit")) {
diff_rename_limit_default = git_config_int(var, value);
return 0;
}
switch (userdiff_config(var, value)) {
case 0: break;
case -1: return -1;
default: return 0;
}
if (!prefixcmp(var, "diff.color.") || !prefixcmp(var, "color.diff.")) {
int slot = parse_diff_color_slot(var, 11);
2009-12-12 20:25:24 +08:00
if (slot < 0)
return 0;
if (!value)
return config_error_nonbool(var);
color_parse(value, var, diff_colors[slot]);
return 0;
}
/* like GNU diff's --suppress-blank-empty option */
if (!strcmp(var, "diff.suppressblankempty") ||
/* for backwards compatibility */
!strcmp(var, "diff.suppress-blank-empty")) {
diff_suppress_blank_empty = git_config_bool(var, value);
return 0;
}
return git_color_default_config(var, value, cb);
}
static char *quote_two(const char *one, const char *two)
{
int need_one = quote_c_style(one, NULL, NULL, 1);
int need_two = quote_c_style(two, NULL, NULL, 1);
struct strbuf res = STRBUF_INIT;
if (need_one + need_two) {
strbuf_addch(&res, '"');
quote_c_style(one, &res, NULL, 1);
quote_c_style(two, &res, NULL, 1);
strbuf_addch(&res, '"');
} else {
strbuf_addstr(&res, one);
strbuf_addstr(&res, two);
}
return strbuf_detach(&res, NULL);
}
static const char *external_diff(void)
{
static const char *external_diff_cmd = NULL;
static int done_preparing = 0;
if (done_preparing)
return external_diff_cmd;
external_diff_cmd = getenv("GIT_EXTERNAL_DIFF");
if (!external_diff_cmd)
external_diff_cmd = external_diff_cmd_cfg;
done_preparing = 1;
return external_diff_cmd;
}
static struct diff_tempfile {
const char *name; /* filename external diff should read from */
char hex[41];
char mode[10];
char tmp_path[PATH_MAX];
} diff_temp[2];
typedef unsigned long (*sane_truncate_fn)(char *line, unsigned long len);
struct emit_callback {
int color_diff;
unsigned ws_rule;
int blank_at_eof_in_preimage;
int blank_at_eof_in_postimage;
int lno_in_preimage;
int lno_in_postimage;
sane_truncate_fn truncate;
const char **label_path;
struct diff_words_data *diff_words;
int *found_changesp;
FILE *file;
struct strbuf *header;
};
static int count_lines(const char *data, int size)
{
int count, ch, completely_empty = 1, nl_just_seen = 0;
count = 0;
while (0 < size--) {
ch = *data++;
if (ch == '\n') {
count++;
nl_just_seen = 1;
completely_empty = 0;
}
else {
nl_just_seen = 0;
completely_empty = 0;
}
}
if (completely_empty)
return 0;
if (!nl_just_seen)
count++; /* no trailing newline */
return count;
}
static int fill_mmfile(mmfile_t *mf, struct diff_filespec *one)
{
if (!DIFF_FILE_VALID(one)) {
mf->ptr = (char *)""; /* does not matter */
mf->size = 0;
return 0;
}
else if (diff_populate_filespec(one, 0))
return -1;
mf->ptr = one->data;
mf->size = one->size;
return 0;
}
static int count_trailing_blank(mmfile_t *mf, unsigned ws_rule)
{
char *ptr = mf->ptr;
long size = mf->size;
int cnt = 0;
if (!size)
return cnt;
ptr += size - 1; /* pointing at the very end */
if (*ptr != '\n')
; /* incomplete line */
else
ptr--; /* skip the last LF */
while (mf->ptr < ptr) {
char *prev_eol;
for (prev_eol = ptr; mf->ptr <= prev_eol; prev_eol--)
if (*prev_eol == '\n')
break;
if (!ws_blank_line(prev_eol + 1, ptr - prev_eol, ws_rule))
break;
cnt++;
ptr = prev_eol - 1;
}
return cnt;
}
static void check_blank_at_eof(mmfile_t *mf1, mmfile_t *mf2,
struct emit_callback *ecbdata)
{
int l1, l2, at;
unsigned ws_rule = ecbdata->ws_rule;
l1 = count_trailing_blank(mf1, ws_rule);
l2 = count_trailing_blank(mf2, ws_rule);
if (l2 <= l1) {
ecbdata->blank_at_eof_in_preimage = 0;
ecbdata->blank_at_eof_in_postimage = 0;
return;
}
at = count_lines(mf1->ptr, mf1->size);
ecbdata->blank_at_eof_in_preimage = (at - l1) + 1;
at = count_lines(mf2->ptr, mf2->size);
ecbdata->blank_at_eof_in_postimage = (at - l2) + 1;
}
static void emit_line_0(FILE *file, const char *set, const char *reset,
int first, const char *line, int len)
{
int has_trailing_newline, has_trailing_carriage_return;
int nofirst;
if (len == 0) {
has_trailing_newline = (first == '\n');
has_trailing_carriage_return = (!has_trailing_newline &&
(first == '\r'));
nofirst = has_trailing_newline || has_trailing_carriage_return;
} else {
has_trailing_newline = (len > 0 && line[len-1] == '\n');
if (has_trailing_newline)
len--;
has_trailing_carriage_return = (len > 0 && line[len-1] == '\r');
if (has_trailing_carriage_return)
len--;
nofirst = 0;
}
if (len || !nofirst) {
fputs(set, file);
if (!nofirst)
fputc(first, file);
fwrite(line, len, 1, file);
fputs(reset, file);
}
if (has_trailing_carriage_return)
fputc('\r', file);
if (has_trailing_newline)
fputc('\n', file);
}
static void emit_line(FILE *file, const char *set, const char *reset,
const char *line, int len)
{
emit_line_0(file, set, reset, line[0], line+1, len-1);
}
static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len)
{
if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) &&
ecbdata->blank_at_eof_in_preimage &&
ecbdata->blank_at_eof_in_postimage &&
ecbdata->blank_at_eof_in_preimage <= ecbdata->lno_in_preimage &&
ecbdata->blank_at_eof_in_postimage <= ecbdata->lno_in_postimage))
return 0;
return ws_blank_line(line, len, ecbdata->ws_rule);
}
static void emit_add_line(const char *reset,
struct emit_callback *ecbdata,
const char *line, int len)
{
const char *ws = diff_get_color(ecbdata->color_diff, DIFF_WHITESPACE);
const char *set = diff_get_color(ecbdata->color_diff, DIFF_FILE_NEW);
if (!*ws)
emit_line_0(ecbdata->file, set, reset, '+', line, len);
else if (new_blank_line_at_eof(ecbdata, line, len))
/* Blank line at EOF - paint '+' as well */
emit_line_0(ecbdata->file, ws, reset, '+', line, len);
else {
/* Emit just the prefix, then the rest. */
emit_line_0(ecbdata->file, set, reset, '+', "", 0);
ws_check_emit(line, len, ecbdata->ws_rule,
ecbdata->file, set, reset, ws);
}
}
static void emit_hunk_header(struct emit_callback *ecbdata,
const char *line, int len)
{
const char *plain = diff_get_color(ecbdata->color_diff, DIFF_PLAIN);
const char *frag = diff_get_color(ecbdata->color_diff, DIFF_FRAGINFO);
const char *func = diff_get_color(ecbdata->color_diff, DIFF_FUNCINFO);
const char *reset = diff_get_color(ecbdata->color_diff, DIFF_RESET);
static const char atat[2] = { '@', '@' };
const char *cp, *ep;
/*
* As a hunk header must begin with "@@ -<old>, +<new> @@",
* it always is at least 10 bytes long.
*/
if (len < 10 ||
memcmp(line, atat, 2) ||
!(ep = memmem(line + 2, len - 2, atat, 2))) {
emit_line(ecbdata->file, plain, reset, line, len);
return;
}
ep += 2; /* skip over @@ */
/* The hunk header in fraginfo color */
emit_line(ecbdata->file, frag, reset, line, ep - line);
/* blank before the func header */
for (cp = ep; ep - line < len; ep++)
if (*ep != ' ' && *ep != '\t')
break;
if (ep != cp)
emit_line(ecbdata->file, plain, reset, cp, ep - cp);
if (ep < line + len)
emit_line(ecbdata->file, func, reset, ep, line + len - ep);
}
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
static struct diff_tempfile *claim_diff_tempfile(void) {
int i;
for (i = 0; i < ARRAY_SIZE(diff_temp); i++)
if (!diff_temp[i].name)
return diff_temp + i;
die("BUG: diff is failing to clean up its tempfiles");
}
static int remove_tempfile_installed;
static void remove_tempfile(void)
{
int i;
for (i = 0; i < ARRAY_SIZE(diff_temp); i++) {
if (diff_temp[i].name == diff_temp[i].tmp_path)
unlink_or_warn(diff_temp[i].name);
diff_temp[i].name = NULL;
}
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
}
static void remove_tempfile_on_signal(int signo)
{
remove_tempfile();
sigchain_pop(signo);
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
raise(signo);
}
static void print_line_count(FILE *file, int count)
{
switch (count) {
case 0:
fprintf(file, "0,0");
break;
case 1:
fprintf(file, "1");
break;
default:
fprintf(file, "1,%d", count);
break;
}
}
static void emit_rewrite_lines(struct emit_callback *ecb,
int prefix, const char *data, int size)
{
const char *endp = NULL;
static const char *nneof = " No newline at end of file\n";
const char *old = diff_get_color(ecb->color_diff, DIFF_FILE_OLD);
const char *reset = diff_get_color(ecb->color_diff, DIFF_RESET);
while (0 < size) {
int len;
endp = memchr(data, '\n', size);
len = endp ? (endp - data + 1) : size;
if (prefix != '+') {
ecb->lno_in_preimage++;
emit_line_0(ecb->file, old, reset, '-',
data, len);
} else {
ecb->lno_in_postimage++;
emit_add_line(reset, ecb, data, len);
}
size -= len;
data += len;
}
if (!endp) {
const char *plain = diff_get_color(ecb->color_diff,
DIFF_PLAIN);
emit_line_0(ecb->file, plain, reset, '\\',
nneof, strlen(nneof));
}
}
static void emit_rewrite_diff(const char *name_a,
const char *name_b,
struct diff_filespec *one,
struct diff_filespec *two,
const char *textconv_one,
const char *textconv_two,
struct diff_options *o)
{
int lc_a, lc_b;
int color_diff = DIFF_OPT_TST(o, COLOR_DIFF);
const char *name_a_tab, *name_b_tab;
const char *metainfo = diff_get_color(color_diff, DIFF_METAINFO);
const char *fraginfo = diff_get_color(color_diff, DIFF_FRAGINFO);
const char *reset = diff_get_color(color_diff, DIFF_RESET);
static struct strbuf a_name = STRBUF_INIT, b_name = STRBUF_INIT;
const char *a_prefix, *b_prefix;
const char *data_one, *data_two;
size_t size_one, size_two;
struct emit_callback ecbdata;
if (diff_mnemonic_prefix && DIFF_OPT_TST(o, REVERSE_DIFF)) {
a_prefix = o->b_prefix;
b_prefix = o->a_prefix;
} else {
a_prefix = o->a_prefix;
b_prefix = o->b_prefix;
}
name_a += (*name_a == '/');
name_b += (*name_b == '/');
name_a_tab = strchr(name_a, ' ') ? "\t" : "";
name_b_tab = strchr(name_b, ' ') ? "\t" : "";
strbuf_reset(&a_name);
strbuf_reset(&b_name);
quote_two_c_style(&a_name, a_prefix, name_a, 0);
quote_two_c_style(&b_name, b_prefix, name_b, 0);
diff_populate_filespec(one, 0);
diff_populate_filespec(two, 0);
if (textconv_one) {
data_one = run_textconv(textconv_one, one, &size_one);
if (!data_one)
die("unable to read files to diff");
}
else {
data_one = one->data;
size_one = one->size;
}
if (textconv_two) {
data_two = run_textconv(textconv_two, two, &size_two);
if (!data_two)
die("unable to read files to diff");
}
else {
data_two = two->data;
size_two = two->size;
}
memset(&ecbdata, 0, sizeof(ecbdata));
ecbdata.color_diff = color_diff;
ecbdata.found_changesp = &o->found_changes;
ecbdata.ws_rule = whitespace_rule(name_b ? name_b : name_a);
ecbdata.file = o->file;
if (ecbdata.ws_rule & WS_BLANK_AT_EOF) {
mmfile_t mf1, mf2;
mf1.ptr = (char *)data_one;
mf2.ptr = (char *)data_two;
mf1.size = size_one;
mf2.size = size_two;
check_blank_at_eof(&mf1, &mf2, &ecbdata);
}
ecbdata.lno_in_preimage = 1;
ecbdata.lno_in_postimage = 1;
lc_a = count_lines(data_one, size_one);
lc_b = count_lines(data_two, size_two);
fprintf(o->file,
"%s--- %s%s%s\n%s+++ %s%s%s\n%s@@ -",
metainfo, a_name.buf, name_a_tab, reset,
metainfo, b_name.buf, name_b_tab, reset, fraginfo);
print_line_count(o->file, lc_a);
fprintf(o->file, " +");
print_line_count(o->file, lc_b);
fprintf(o->file, " @@%s\n", reset);
if (lc_a)
emit_rewrite_lines(&ecbdata, '-', data_one, size_one);
if (lc_b)
emit_rewrite_lines(&ecbdata, '+', data_two, size_two);
}
struct diff_words_buffer {
mmfile_t text;
long alloc;
2009-01-18 00:29:44 +08:00
struct diff_words_orig {
const char *begin, *end;
} *orig;
int orig_nr, orig_alloc;
};
static void diff_words_append(char *line, unsigned long len,
struct diff_words_buffer *buffer)
{
ALLOC_GROW(buffer->text.ptr, buffer->text.size + len, buffer->alloc);
line++;
len--;
memcpy(buffer->text.ptr + buffer->text.size, line, len);
buffer->text.size += len;
buffer->text.ptr[buffer->text.size] = '\0';
}
struct diff_words_data {
struct diff_words_buffer minus, plus;
2009-01-18 00:29:44 +08:00
const char *current_plus;
FILE *file;
regex_t *word_regex;
};
static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
{
struct diff_words_data *diff_words = priv;
2009-01-18 00:29:44 +08:00
int minus_first, minus_len, plus_first, plus_len;
const char *minus_begin, *minus_end, *plus_begin, *plus_end;
2009-01-18 00:29:44 +08:00
if (line[0] != '@' || parse_hunk_header(line, len,
&minus_first, &minus_len, &plus_first, &plus_len))
return;
2009-01-18 00:29:44 +08:00
/* POSIX requires that first be decremented by one if len == 0... */
if (minus_len) {
minus_begin = diff_words->minus.orig[minus_first].begin;
minus_end =
diff_words->minus.orig[minus_first + minus_len - 1].end;
} else
minus_begin = minus_end =
diff_words->minus.orig[minus_first].end;
if (plus_len) {
plus_begin = diff_words->plus.orig[plus_first].begin;
plus_end = diff_words->plus.orig[plus_first + plus_len - 1].end;
} else
plus_begin = plus_end = diff_words->plus.orig[plus_first].end;
if (diff_words->current_plus != plus_begin)
fwrite(diff_words->current_plus,
plus_begin - diff_words->current_plus, 1,
diff_words->file);
if (minus_begin != minus_end)
color_fwrite_lines(diff_words->file,
diff_get_color(1, DIFF_FILE_OLD),
minus_end - minus_begin, minus_begin);
if (plus_begin != plus_end)
color_fwrite_lines(diff_words->file,
diff_get_color(1, DIFF_FILE_NEW),
plus_end - plus_begin, plus_begin);
diff_words->current_plus = plus_end;
}
/* This function starts looking at *begin, and returns 0 iff a word was found. */
static int find_word_boundaries(mmfile_t *buffer, regex_t *word_regex,
int *begin, int *end)
{
if (word_regex && *begin < buffer->size) {
regmatch_t match[1];
if (!regexec(word_regex, buffer->ptr + *begin, 1, match, 0)) {
char *p = memchr(buffer->ptr + *begin + match[0].rm_so,
'\n', match[0].rm_eo - match[0].rm_so);
*end = p ? p - buffer->ptr : match[0].rm_eo + *begin;
*begin += match[0].rm_so;
return *begin >= *end;
}
return -1;
}
/* find the next word */
while (*begin < buffer->size && isspace(buffer->ptr[*begin]))
(*begin)++;
if (*begin >= buffer->size)
return -1;
/* find the end of the word */
*end = *begin + 1;
while (*end < buffer->size && !isspace(buffer->ptr[*end]))
(*end)++;
return 0;
}
/*
2009-01-18 00:29:44 +08:00
* This function splits the words in buffer->text, stores the list with
* newline separator into out, and saves the offsets of the original words
* in buffer->orig.
*/
static void diff_words_fill(struct diff_words_buffer *buffer, mmfile_t *out,
regex_t *word_regex)
{
2009-01-18 00:29:44 +08:00
int i, j;
long alloc = 0;
2009-01-18 00:29:44 +08:00
out->size = 0;
out->ptr = NULL;
2009-01-18 00:29:44 +08:00
/* fake an empty "0th" word */
ALLOC_GROW(buffer->orig, 1, buffer->orig_alloc);
buffer->orig[0].begin = buffer->orig[0].end = buffer->text.ptr;
buffer->orig_nr = 1;
for (i = 0; i < buffer->text.size; i++) {
if (find_word_boundaries(&buffer->text, word_regex, &i, &j))
return;
2009-01-18 00:29:44 +08:00
/* store original boundaries */
ALLOC_GROW(buffer->orig, buffer->orig_nr + 1,
buffer->orig_alloc);
buffer->orig[buffer->orig_nr].begin = buffer->text.ptr + i;
buffer->orig[buffer->orig_nr].end = buffer->text.ptr + j;
buffer->orig_nr++;
/* store one word */
ALLOC_GROW(out->ptr, out->size + j - i + 1, alloc);
2009-01-18 00:29:44 +08:00
memcpy(out->ptr + out->size, buffer->text.ptr + i, j - i);
out->ptr[out->size + j - i] = '\n';
out->size += j - i + 1;
i = j - 1;
}
}
/* this executes the word diff on the accumulated buffers */
static void diff_words_show(struct diff_words_data *diff_words)
{
xpparam_t xpp;
xdemitconf_t xecfg;
xdemitcb_t ecb;
mmfile_t minus, plus;
2009-01-18 00:29:44 +08:00
/* special case: only removal */
if (!diff_words->plus.text.size) {
color_fwrite_lines(diff_words->file,
diff_get_color(1, DIFF_FILE_OLD),
diff_words->minus.text.size, diff_words->minus.text.ptr);
diff_words->minus.text.size = 0;
return;
}
diff_words->current_plus = diff_words->plus.text.ptr;
memset(&xpp, 0, sizeof(xpp));
memset(&xecfg, 0, sizeof(xecfg));
diff_words_fill(&diff_words->minus, &minus, diff_words->word_regex);
diff_words_fill(&diff_words->plus, &plus, diff_words->word_regex);
xpp.flags = XDF_NEED_MINIMAL;
/* as only the hunk header will be parsed, we need a 0-context */
2009-01-18 00:29:44 +08:00
xecfg.ctxlen = 0;
xdi_diff_outf(&minus, &plus, fn_out_diff_words_aux, diff_words,
&xpp, &xecfg, &ecb);
free(minus.ptr);
free(plus.ptr);
2009-01-18 00:29:44 +08:00
if (diff_words->current_plus != diff_words->plus.text.ptr +
diff_words->plus.text.size)
fwrite(diff_words->current_plus,
diff_words->plus.text.ptr + diff_words->plus.text.size
- diff_words->current_plus, 1,
diff_words->file);
diff_words->minus.text.size = diff_words->plus.text.size = 0;
}
2009-10-31 01:09:06 +08:00
/* In "color-words" mode, show word-diff of words accumulated in the buffer */
static void diff_words_flush(struct emit_callback *ecbdata)
{
if (ecbdata->diff_words->minus.text.size ||
ecbdata->diff_words->plus.text.size)
diff_words_show(ecbdata->diff_words);
}
static void free_diff_words_data(struct emit_callback *ecbdata)
{
if (ecbdata->diff_words) {
2009-10-31 01:09:06 +08:00
diff_words_flush(ecbdata);
Avoid unnecessary "if-before-free" tests. This change removes all obvious useless if-before-free tests. E.g., it replaces code like this: if (some_expression) free (some_expression); with the now-equivalent: free (some_expression); It is equivalent not just because POSIX has required free(NULL) to work for a long time, but simply because it has worked for so long that no reasonable porting target fails the test. Here's some evidence from nearly 1.5 years ago: http://www.winehq.org/pipermail/wine-patches/2006-October/031544.html FYI, the change below was prepared by running the following: git ls-files -z | xargs -0 \ perl -0x3b -pi -e \ 's/\bif\s*\(\s*(\S+?)(?:\s*!=\s*NULL)?\s*\)\s+(free\s*\(\s*\1\s*\))/$2/s' Note however, that it doesn't handle brace-enclosed blocks like "if (x) { free (x); }". But that's ok, since there were none like that in git sources. Beware: if you do use the above snippet, note that it can produce syntactically invalid C code. That happens when the affected "if"-statement has a matching "else". E.g., it would transform this if (x) free (x); else foo (); into this: free (x); else foo (); There were none of those here, either. If you're interested in automating detection of the useless tests, you might like the useless-if-before-free script in gnulib: [it *does* detect brace-enclosed free statements, and has a --name=S option to make it detect free-like functions with different names] http://git.sv.gnu.org/gitweb/?p=gnulib.git;a=blob;f=build-aux/useless-if-before-free Addendum: Remove one more (in imap-send.c), spotted by Jean-Luc Herren <jlh@gmx.ch>. Signed-off-by: Jim Meyering <meyering@redhat.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-01 01:26:32 +08:00
free (ecbdata->diff_words->minus.text.ptr);
2009-01-18 00:29:44 +08:00
free (ecbdata->diff_words->minus.orig);
Avoid unnecessary "if-before-free" tests. This change removes all obvious useless if-before-free tests. E.g., it replaces code like this: if (some_expression) free (some_expression); with the now-equivalent: free (some_expression); It is equivalent not just because POSIX has required free(NULL) to work for a long time, but simply because it has worked for so long that no reasonable porting target fails the test. Here's some evidence from nearly 1.5 years ago: http://www.winehq.org/pipermail/wine-patches/2006-October/031544.html FYI, the change below was prepared by running the following: git ls-files -z | xargs -0 \ perl -0x3b -pi -e \ 's/\bif\s*\(\s*(\S+?)(?:\s*!=\s*NULL)?\s*\)\s+(free\s*\(\s*\1\s*\))/$2/s' Note however, that it doesn't handle brace-enclosed blocks like "if (x) { free (x); }". But that's ok, since there were none like that in git sources. Beware: if you do use the above snippet, note that it can produce syntactically invalid C code. That happens when the affected "if"-statement has a matching "else". E.g., it would transform this if (x) free (x); else foo (); into this: free (x); else foo (); There were none of those here, either. If you're interested in automating detection of the useless tests, you might like the useless-if-before-free script in gnulib: [it *does* detect brace-enclosed free statements, and has a --name=S option to make it detect free-like functions with different names] http://git.sv.gnu.org/gitweb/?p=gnulib.git;a=blob;f=build-aux/useless-if-before-free Addendum: Remove one more (in imap-send.c), spotted by Jean-Luc Herren <jlh@gmx.ch>. Signed-off-by: Jim Meyering <meyering@redhat.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-01 01:26:32 +08:00
free (ecbdata->diff_words->plus.text.ptr);
2009-01-18 00:29:44 +08:00
free (ecbdata->diff_words->plus.orig);
free(ecbdata->diff_words->word_regex);
free(ecbdata->diff_words);
ecbdata->diff_words = NULL;
}
}
const char *diff_get_color(int diff_use_color, enum color_diff ix)
{
if (diff_use_color)
return diff_colors[ix];
return "";
}
static unsigned long sane_truncate_line(struct emit_callback *ecb, char *line, unsigned long len)
{
const char *cp;
unsigned long allot;
size_t l = len;
if (ecb->truncate)
return ecb->truncate(line, len);
cp = line;
allot = l;
while (0 < l) {
(void) utf8_width(&cp, &l);
if (!cp)
break; /* truncated in the middle? */
}
return allot - l;
}
static void find_lno(const char *line, struct emit_callback *ecbdata)
{
const char *p;
ecbdata->lno_in_preimage = 0;
ecbdata->lno_in_postimage = 0;
p = strchr(line, '-');
if (!p)
return; /* cannot happen */
ecbdata->lno_in_preimage = strtol(p + 1, NULL, 10);
p = strchr(p, '+');
if (!p)
return; /* cannot happen */
ecbdata->lno_in_postimage = strtol(p + 1, NULL, 10);
}
static void fn_out_consume(void *priv, char *line, unsigned long len)
{
struct emit_callback *ecbdata = priv;
const char *meta = diff_get_color(ecbdata->color_diff, DIFF_METAINFO);
const char *plain = diff_get_color(ecbdata->color_diff, DIFF_PLAIN);
const char *reset = diff_get_color(ecbdata->color_diff, DIFF_RESET);
if (ecbdata->header) {
fprintf(ecbdata->file, "%s", ecbdata->header->buf);
strbuf_reset(ecbdata->header);
ecbdata->header = NULL;
}
*(ecbdata->found_changesp) = 1;
if (ecbdata->label_path[0]) {
const char *name_a_tab, *name_b_tab;
name_a_tab = strchr(ecbdata->label_path[0], ' ') ? "\t" : "";
name_b_tab = strchr(ecbdata->label_path[1], ' ') ? "\t" : "";
fprintf(ecbdata->file, "%s--- %s%s%s\n",
meta, ecbdata->label_path[0], reset, name_a_tab);
fprintf(ecbdata->file, "%s+++ %s%s%s\n",
meta, ecbdata->label_path[1], reset, name_b_tab);
ecbdata->label_path[0] = ecbdata->label_path[1] = NULL;
}
if (diff_suppress_blank_empty
&& len == 2 && line[0] == ' ' && line[1] == '\n') {
line[0] = '\n';
len = 1;
}
if (line[0] == '@') {
2009-10-31 01:09:06 +08:00
if (ecbdata->diff_words)
diff_words_flush(ecbdata);
len = sane_truncate_line(ecbdata, line, len);
find_lno(line, ecbdata);
emit_hunk_header(ecbdata, line, len);
if (line[len-1] != '\n')
putc('\n', ecbdata->file);
return;
}
if (len < 1) {
emit_line(ecbdata->file, reset, reset, line, len);
return;
}
if (ecbdata->diff_words) {
if (line[0] == '-') {
diff_words_append(line, len,
&ecbdata->diff_words->minus);
return;
} else if (line[0] == '+') {
diff_words_append(line, len,
&ecbdata->diff_words->plus);
return;
}
2009-10-31 01:09:06 +08:00
diff_words_flush(ecbdata);
line++;
len--;
emit_line(ecbdata->file, plain, reset, line, len);
return;
}
if (line[0] != '+') {
const char *color =
diff_get_color(ecbdata->color_diff,
line[0] == '-' ? DIFF_FILE_OLD : DIFF_PLAIN);
ecbdata->lno_in_preimage++;
if (line[0] == ' ')
ecbdata->lno_in_postimage++;
emit_line(ecbdata->file, color, reset, line, len);
} else {
ecbdata->lno_in_postimage++;
emit_add_line(reset, ecbdata, line + 1, len - 1);
}
}
static char *pprint_rename(const char *a, const char *b)
{
const char *old = a;
const char *new = b;
struct strbuf name = STRBUF_INIT;
int pfx_length, sfx_length;
int len_a = strlen(a);
int len_b = strlen(b);
int a_midlen, b_midlen;
int qlen_a = quote_c_style(a, NULL, NULL, 0);
int qlen_b = quote_c_style(b, NULL, NULL, 0);
if (qlen_a || qlen_b) {
quote_c_style(a, &name, NULL, 0);
strbuf_addstr(&name, " => ");
quote_c_style(b, &name, NULL, 0);
return strbuf_detach(&name, NULL);
}
/* Find common prefix */
pfx_length = 0;
while (*old && *new && *old == *new) {
if (*old == '/')
pfx_length = old - a + 1;
old++;
new++;
}
/* Find common suffix */
old = a + len_a;
new = b + len_b;
sfx_length = 0;
while (a <= old && b <= new && *old == *new) {
if (*old == '/')
sfx_length = len_a - (old - a);
old--;
new--;
}
/*
* pfx{mid-a => mid-b}sfx
* {pfx-a => pfx-b}sfx
* pfx{sfx-a => sfx-b}
* name-a => name-b
*/
a_midlen = len_a - pfx_length - sfx_length;
b_midlen = len_b - pfx_length - sfx_length;
if (a_midlen < 0)
a_midlen = 0;
if (b_midlen < 0)
b_midlen = 0;
strbuf_grow(&name, pfx_length + a_midlen + b_midlen + sfx_length + 7);
if (pfx_length + sfx_length) {
strbuf_add(&name, a, pfx_length);
strbuf_addch(&name, '{');
}
strbuf_add(&name, a + pfx_length, a_midlen);
strbuf_addstr(&name, " => ");
strbuf_add(&name, b + pfx_length, b_midlen);
if (pfx_length + sfx_length) {
strbuf_addch(&name, '}');
strbuf_add(&name, a + len_a - sfx_length, sfx_length);
}
return strbuf_detach(&name, NULL);
}
struct diffstat_t {
int nr;
int alloc;
struct diffstat_file {
char *from_name;
char *name;
char *print_name;
unsigned is_unmerged:1;
unsigned is_binary:1;
unsigned is_renamed:1;
unsigned int added, deleted;
} **files;
};
static struct diffstat_file *diffstat_add(struct diffstat_t *diffstat,
const char *name_a,
const char *name_b)
{
struct diffstat_file *x;
x = xcalloc(sizeof (*x), 1);
if (diffstat->nr == diffstat->alloc) {
diffstat->alloc = alloc_nr(diffstat->alloc);
diffstat->files = xrealloc(diffstat->files,
diffstat->alloc * sizeof(x));
}
diffstat->files[diffstat->nr++] = x;
if (name_b) {
x->from_name = xstrdup(name_a);
x->name = xstrdup(name_b);
x->is_renamed = 1;
}
else {
x->from_name = NULL;
x->name = xstrdup(name_a);
}
return x;
}
static void diffstat_consume(void *priv, char *line, unsigned long len)
{
struct diffstat_t *diffstat = priv;
struct diffstat_file *x = diffstat->files[diffstat->nr - 1];
if (line[0] == '+')
x->added++;
else if (line[0] == '-')
x->deleted++;
}
const char mime_boundary_leader[] = "------------";
static int scale_linear(int it, int width, int max_change)
{
/*
* make sure that at least one '-' is printed if there were deletions,
* and likewise for '+'.
*/
if (max_change < 2)
return it;
return ((it - 1) * (width - 1) + max_change - 1) / (max_change - 1);
}
static void show_name(FILE *file,
const char *prefix, const char *name, int len)
{
fprintf(file, " %s%-*s |", prefix, len, name);
}
static void show_graph(FILE *file, char ch, int cnt, const char *set, const char *reset)
{
if (cnt <= 0)
return;
fprintf(file, "%s", set);
while (cnt--)
putc(ch, file);
fprintf(file, "%s", reset);
}
static void fill_print_name(struct diffstat_file *file)
{
char *pname;
if (file->print_name)
return;
if (!file->is_renamed) {
struct strbuf buf = STRBUF_INIT;
if (quote_c_style(file->name, &buf, NULL, 0)) {
pname = strbuf_detach(&buf, NULL);
} else {
pname = file->name;
strbuf_release(&buf);
}
} else {
pname = pprint_rename(file->from_name, file->name);
}
file->print_name = pname;
}
static void show_stats(struct diffstat_t *data, struct diff_options *options)
{
int i, len, add, del, adds = 0, dels = 0;
int max_change = 0, max_len = 0;
int total_files = data->nr;
int width, name_width;
const char *reset, *set, *add_c, *del_c;
if (data->nr == 0)
return;
width = options->stat_width ? options->stat_width : 80;
name_width = options->stat_name_width ? options->stat_name_width : 50;
/* Sanity: give at least 5 columns to the graph,
* but leave at least 10 columns for the name.
*/
if (width < 25)
width = 25;
if (name_width < 10)
name_width = 10;
else if (width < name_width + 15)
name_width = width - 15;
/* Find the longest filename and max number of changes */
reset = diff_get_color_opt(options, DIFF_RESET);
set = diff_get_color_opt(options, DIFF_PLAIN);
add_c = diff_get_color_opt(options, DIFF_FILE_NEW);
del_c = diff_get_color_opt(options, DIFF_FILE_OLD);
for (i = 0; i < data->nr; i++) {
struct diffstat_file *file = data->files[i];
int change = file->added + file->deleted;
fill_print_name(file);
len = strlen(file->print_name);
if (max_len < len)
max_len = len;
if (file->is_binary || file->is_unmerged)
continue;
if (max_change < change)
max_change = change;
}
/* Compute the width of the graph part;
* 10 is for one blank at the beginning of the line plus
* " | count " between the name and the graph.
*
* From here on, name_width is the width of the name area,
* and width is the width of the graph area.
*/
name_width = (name_width < max_len) ? name_width : max_len;
if (width < (name_width + 10) + max_change)
width = width - (name_width + 10);
else
width = max_change;
for (i = 0; i < data->nr; i++) {
const char *prefix = "";
char *name = data->files[i]->print_name;
int added = data->files[i]->added;
int deleted = data->files[i]->deleted;
int name_len;
/*
* "scale" the filename
*/
len = name_width;
name_len = strlen(name);
if (name_width < name_len) {
char *slash;
prefix = "...";
len -= 3;
name += name_len - len;
slash = strchr(name, '/');
if (slash)
name = slash;
}
if (data->files[i]->is_binary) {
show_name(options->file, prefix, name, len);
fprintf(options->file, " Bin ");
fprintf(options->file, "%s%d%s", del_c, deleted, reset);
fprintf(options->file, " -> ");
fprintf(options->file, "%s%d%s", add_c, added, reset);
fprintf(options->file, " bytes");
fprintf(options->file, "\n");
continue;
}
else if (data->files[i]->is_unmerged) {
show_name(options->file, prefix, name, len);
fprintf(options->file, " Unmerged\n");
continue;
}
else if (!data->files[i]->is_renamed &&
(added + deleted == 0)) {
total_files--;
continue;
}
/*
* scale the add/delete
*/
add = added;
del = deleted;
adds += add;
dels += del;
if (width <= max_change) {
add = scale_linear(add, width, max_change);
del = scale_linear(del, width, max_change);
}
show_name(options->file, prefix, name, len);
fprintf(options->file, "%5d%s", added + deleted,
added + deleted ? " " : "");
show_graph(options->file, '+', add, add_c, reset);
show_graph(options->file, '-', del, del_c, reset);
fprintf(options->file, "\n");
}
fprintf(options->file,
" %d files changed, %d insertions(+), %d deletions(-)\n",
total_files, adds, dels);
}
static void show_shortstats(struct diffstat_t *data, struct diff_options *options)
{
int i, adds = 0, dels = 0, total_files = data->nr;
if (data->nr == 0)
return;
for (i = 0; i < data->nr; i++) {
if (!data->files[i]->is_binary &&
!data->files[i]->is_unmerged) {
int added = data->files[i]->added;
int deleted= data->files[i]->deleted;
if (!data->files[i]->is_renamed &&
(added + deleted == 0)) {
total_files--;
} else {
adds += added;
dels += deleted;
}
}
}
fprintf(options->file, " %d files changed, %d insertions(+), %d deletions(-)\n",
total_files, adds, dels);
}
static void show_numstat(struct diffstat_t *data, struct diff_options *options)
{
int i;
if (data->nr == 0)
return;
for (i = 0; i < data->nr; i++) {
struct diffstat_file *file = data->files[i];
if (file->is_binary)
fprintf(options->file, "-\t-\t");
else
fprintf(options->file,
"%d\t%d\t", file->added, file->deleted);
if (options->line_termination) {
fill_print_name(file);
if (!file->is_renamed)
write_name_quoted(file->name, options->file,
options->line_termination);
else {
fputs(file->print_name, options->file);
putc(options->line_termination, options->file);
}
} else {
if (file->is_renamed) {
putc('\0', options->file);
write_name_quoted(file->from_name, options->file, '\0');
}
write_name_quoted(file->name, options->file, '\0');
}
}
}
struct dirstat_file {
const char *name;
unsigned long changed;
Add "--dirstat" for some directory statistics This adds a new form of overview diffstat output, doing something that I have occasionally ended up doing manually (and badly, because it's actually pretty nasty to do), and that I think is very useful for an project like the kernel that has a fairly deep and well-separated directory structure with semantic meaning. What I mean by that is that it's often interesting to see exactly which sub-directories are impacted by a patch, and to what degree - even if you don't perhaps care so much about the individual files themselves. What makes the concept more interesting is that the "impact" is often hierarchical: in the kernel, for example, something could either have a very localized impact to "fs/ext3/" and then it's interesting to see that such a patch changes mostly that subdirectory, but you could have another patch that changes some generic VFS-layer issue which affects _many_ subdirectories that are all under "fs/", but none - or perhaps just a couple of them - of the individual filesystems are interesting in themselves. So what commonly happens is that you may have big changes in a specific sub-subdirectory, but still also significant separate changes to the subdirectory leading up to that - maybe you have significant VFS-level changes, but *also* changes under that VFS layer in the NFS-specific directories, for example. In that case, you do want the low-level parts that are significant to show up, but then the insignificant ones should show up as under the more generic top-level directory. This patch shows all of that with "--dirstat". The output can be either something simple like commit 81772fe... Author: Thomas Gleixner <tglx@linutronix.de> Date: Sun Feb 10 23:57:36 2008 +0100 x86: remove over noisy debug printk pageattr-test.c contains a noisy debug printk that people reported. The condition under which it prints (randomly tapping into a mem_map[] hole and not being able to c_p_a() there) is valid behavior and not interesting to report. Remove it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 100.0% arch/x86/mm/ or something much more complex like commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 15.3% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ where that latter example is an example of significant work in some individual fs/*/ subdirectories (like the patches to reiserfs accounting for 7.6% of the whole), but then discounting those individual filesystems, there's also 15.3% other "random" things that weren't worth reporting on their oen left over under fs/ in general (either in that directory itself, or in subdirectories of fs/ that didn't have enough changes to be reported individually). I'd like to stress that the "15.3% fs/" mentioned above is the stuff that is under fs/ but that was _not_ significant enough to report on its own. So the above does _not_ mean that 15.3% of the work was under fs/ per se, because that 15.3% does *not* include the already-reported 7.6% of afs, 7.6% of fuse etc. If you want to enable "cumulative" directory statistics, you can use the "--cumulative" flag, which adds up percentages recursively even when they have been already reported for a sub-directory. That cumulative output is disabled if *all* of the changes in one subdirectory come from a deeper subdirectory, to avoid repeating subdirectories all the way to the root. For an example of the cumulative reporting, the above commit becomes commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 61.5% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ in which the commit percentages now obviously add up to much more than 100%: now the changes that were already reported for the sub-directories under fs/ are then cumulatively included in the whole percentage of fs/ (ie now shows 61.5% as opposed to the 15.3% without the cumulative reporting). The default reporting limit has been arbitrarily set at 3%, which seems to be a pretty good cut-off, but you can specify the cut-off manually by giving it as an option parameter (eg "--dirstat=5" makes the cut-off be at 5% instead) NOTE! The percentages are purely about the total lines added and removed, not anything smarter (or dumber) than that. Also note that you should not generally expect things to add up to 100%: not only does it round down, we don't report leftover scraps (they add up to the top-level change count, but we don't even bother reporting that, it only reports subdirectories). Quite frankly, as a top-level manager this is really convenient for me, but it's going to be very boring for git itself since there are few subdirectories. Also, don't expect things to make tons of sense if you combine this with "-M" and there are cross-directory renames etc. But even for git itself, you can get some fun statistics. Try out git log --dirstat and see the occasional mentions of things like Documentation/, git-gui/, gitweb/ and gitk-git/. Or try out something like git diff --dirstat v1.5.0..v1.5.4 which does kind of git an overview that shows *something*. But in general, the output is more exciting for big projects with deeper structure, and doing a git diff --dirstat v2.6.24..v2.6.25-rc1 on the kernel is what I actually wrote this for! Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 05:26:31 +08:00
};
struct dirstat_dir {
struct dirstat_file *files;
int alloc, nr, percent, cumulative;
};
static long gather_dirstat(FILE *file, struct dirstat_dir *dir, unsigned long changed, const char *base, int baselen)
Add "--dirstat" for some directory statistics This adds a new form of overview diffstat output, doing something that I have occasionally ended up doing manually (and badly, because it's actually pretty nasty to do), and that I think is very useful for an project like the kernel that has a fairly deep and well-separated directory structure with semantic meaning. What I mean by that is that it's often interesting to see exactly which sub-directories are impacted by a patch, and to what degree - even if you don't perhaps care so much about the individual files themselves. What makes the concept more interesting is that the "impact" is often hierarchical: in the kernel, for example, something could either have a very localized impact to "fs/ext3/" and then it's interesting to see that such a patch changes mostly that subdirectory, but you could have another patch that changes some generic VFS-layer issue which affects _many_ subdirectories that are all under "fs/", but none - or perhaps just a couple of them - of the individual filesystems are interesting in themselves. So what commonly happens is that you may have big changes in a specific sub-subdirectory, but still also significant separate changes to the subdirectory leading up to that - maybe you have significant VFS-level changes, but *also* changes under that VFS layer in the NFS-specific directories, for example. In that case, you do want the low-level parts that are significant to show up, but then the insignificant ones should show up as under the more generic top-level directory. This patch shows all of that with "--dirstat". The output can be either something simple like commit 81772fe... Author: Thomas Gleixner <tglx@linutronix.de> Date: Sun Feb 10 23:57:36 2008 +0100 x86: remove over noisy debug printk pageattr-test.c contains a noisy debug printk that people reported. The condition under which it prints (randomly tapping into a mem_map[] hole and not being able to c_p_a() there) is valid behavior and not interesting to report. Remove it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 100.0% arch/x86/mm/ or something much more complex like commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 15.3% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ where that latter example is an example of significant work in some individual fs/*/ subdirectories (like the patches to reiserfs accounting for 7.6% of the whole), but then discounting those individual filesystems, there's also 15.3% other "random" things that weren't worth reporting on their oen left over under fs/ in general (either in that directory itself, or in subdirectories of fs/ that didn't have enough changes to be reported individually). I'd like to stress that the "15.3% fs/" mentioned above is the stuff that is under fs/ but that was _not_ significant enough to report on its own. So the above does _not_ mean that 15.3% of the work was under fs/ per se, because that 15.3% does *not* include the already-reported 7.6% of afs, 7.6% of fuse etc. If you want to enable "cumulative" directory statistics, you can use the "--cumulative" flag, which adds up percentages recursively even when they have been already reported for a sub-directory. That cumulative output is disabled if *all* of the changes in one subdirectory come from a deeper subdirectory, to avoid repeating subdirectories all the way to the root. For an example of the cumulative reporting, the above commit becomes commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 61.5% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ in which the commit percentages now obviously add up to much more than 100%: now the changes that were already reported for the sub-directories under fs/ are then cumulatively included in the whole percentage of fs/ (ie now shows 61.5% as opposed to the 15.3% without the cumulative reporting). The default reporting limit has been arbitrarily set at 3%, which seems to be a pretty good cut-off, but you can specify the cut-off manually by giving it as an option parameter (eg "--dirstat=5" makes the cut-off be at 5% instead) NOTE! The percentages are purely about the total lines added and removed, not anything smarter (or dumber) than that. Also note that you should not generally expect things to add up to 100%: not only does it round down, we don't report leftover scraps (they add up to the top-level change count, but we don't even bother reporting that, it only reports subdirectories). Quite frankly, as a top-level manager this is really convenient for me, but it's going to be very boring for git itself since there are few subdirectories. Also, don't expect things to make tons of sense if you combine this with "-M" and there are cross-directory renames etc. But even for git itself, you can get some fun statistics. Try out git log --dirstat and see the occasional mentions of things like Documentation/, git-gui/, gitweb/ and gitk-git/. Or try out something like git diff --dirstat v1.5.0..v1.5.4 which does kind of git an overview that shows *something*. But in general, the output is more exciting for big projects with deeper structure, and doing a git diff --dirstat v2.6.24..v2.6.25-rc1 on the kernel is what I actually wrote this for! Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 05:26:31 +08:00
{
unsigned long this_dir = 0;
unsigned int sources = 0;
while (dir->nr) {
struct dirstat_file *f = dir->files;
Add "--dirstat" for some directory statistics This adds a new form of overview diffstat output, doing something that I have occasionally ended up doing manually (and badly, because it's actually pretty nasty to do), and that I think is very useful for an project like the kernel that has a fairly deep and well-separated directory structure with semantic meaning. What I mean by that is that it's often interesting to see exactly which sub-directories are impacted by a patch, and to what degree - even if you don't perhaps care so much about the individual files themselves. What makes the concept more interesting is that the "impact" is often hierarchical: in the kernel, for example, something could either have a very localized impact to "fs/ext3/" and then it's interesting to see that such a patch changes mostly that subdirectory, but you could have another patch that changes some generic VFS-layer issue which affects _many_ subdirectories that are all under "fs/", but none - or perhaps just a couple of them - of the individual filesystems are interesting in themselves. So what commonly happens is that you may have big changes in a specific sub-subdirectory, but still also significant separate changes to the subdirectory leading up to that - maybe you have significant VFS-level changes, but *also* changes under that VFS layer in the NFS-specific directories, for example. In that case, you do want the low-level parts that are significant to show up, but then the insignificant ones should show up as under the more generic top-level directory. This patch shows all of that with "--dirstat". The output can be either something simple like commit 81772fe... Author: Thomas Gleixner <tglx@linutronix.de> Date: Sun Feb 10 23:57:36 2008 +0100 x86: remove over noisy debug printk pageattr-test.c contains a noisy debug printk that people reported. The condition under which it prints (randomly tapping into a mem_map[] hole and not being able to c_p_a() there) is valid behavior and not interesting to report. Remove it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 100.0% arch/x86/mm/ or something much more complex like commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 15.3% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ where that latter example is an example of significant work in some individual fs/*/ subdirectories (like the patches to reiserfs accounting for 7.6% of the whole), but then discounting those individual filesystems, there's also 15.3% other "random" things that weren't worth reporting on their oen left over under fs/ in general (either in that directory itself, or in subdirectories of fs/ that didn't have enough changes to be reported individually). I'd like to stress that the "15.3% fs/" mentioned above is the stuff that is under fs/ but that was _not_ significant enough to report on its own. So the above does _not_ mean that 15.3% of the work was under fs/ per se, because that 15.3% does *not* include the already-reported 7.6% of afs, 7.6% of fuse etc. If you want to enable "cumulative" directory statistics, you can use the "--cumulative" flag, which adds up percentages recursively even when they have been already reported for a sub-directory. That cumulative output is disabled if *all* of the changes in one subdirectory come from a deeper subdirectory, to avoid repeating subdirectories all the way to the root. For an example of the cumulative reporting, the above commit becomes commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 61.5% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ in which the commit percentages now obviously add up to much more than 100%: now the changes that were already reported for the sub-directories under fs/ are then cumulatively included in the whole percentage of fs/ (ie now shows 61.5% as opposed to the 15.3% without the cumulative reporting). The default reporting limit has been arbitrarily set at 3%, which seems to be a pretty good cut-off, but you can specify the cut-off manually by giving it as an option parameter (eg "--dirstat=5" makes the cut-off be at 5% instead) NOTE! The percentages are purely about the total lines added and removed, not anything smarter (or dumber) than that. Also note that you should not generally expect things to add up to 100%: not only does it round down, we don't report leftover scraps (they add up to the top-level change count, but we don't even bother reporting that, it only reports subdirectories). Quite frankly, as a top-level manager this is really convenient for me, but it's going to be very boring for git itself since there are few subdirectories. Also, don't expect things to make tons of sense if you combine this with "-M" and there are cross-directory renames etc. But even for git itself, you can get some fun statistics. Try out git log --dirstat and see the occasional mentions of things like Documentation/, git-gui/, gitweb/ and gitk-git/. Or try out something like git diff --dirstat v1.5.0..v1.5.4 which does kind of git an overview that shows *something*. But in general, the output is more exciting for big projects with deeper structure, and doing a git diff --dirstat v2.6.24..v2.6.25-rc1 on the kernel is what I actually wrote this for! Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 05:26:31 +08:00
int namelen = strlen(f->name);
unsigned long this;
char *slash;
if (namelen < baselen)
break;
if (memcmp(f->name, base, baselen))
break;
slash = strchr(f->name + baselen, '/');
if (slash) {
int newbaselen = slash + 1 - f->name;
this = gather_dirstat(file, dir, changed, f->name, newbaselen);
Add "--dirstat" for some directory statistics This adds a new form of overview diffstat output, doing something that I have occasionally ended up doing manually (and badly, because it's actually pretty nasty to do), and that I think is very useful for an project like the kernel that has a fairly deep and well-separated directory structure with semantic meaning. What I mean by that is that it's often interesting to see exactly which sub-directories are impacted by a patch, and to what degree - even if you don't perhaps care so much about the individual files themselves. What makes the concept more interesting is that the "impact" is often hierarchical: in the kernel, for example, something could either have a very localized impact to "fs/ext3/" and then it's interesting to see that such a patch changes mostly that subdirectory, but you could have another patch that changes some generic VFS-layer issue which affects _many_ subdirectories that are all under "fs/", but none - or perhaps just a couple of them - of the individual filesystems are interesting in themselves. So what commonly happens is that you may have big changes in a specific sub-subdirectory, but still also significant separate changes to the subdirectory leading up to that - maybe you have significant VFS-level changes, but *also* changes under that VFS layer in the NFS-specific directories, for example. In that case, you do want the low-level parts that are significant to show up, but then the insignificant ones should show up as under the more generic top-level directory. This patch shows all of that with "--dirstat". The output can be either something simple like commit 81772fe... Author: Thomas Gleixner <tglx@linutronix.de> Date: Sun Feb 10 23:57:36 2008 +0100 x86: remove over noisy debug printk pageattr-test.c contains a noisy debug printk that people reported. The condition under which it prints (randomly tapping into a mem_map[] hole and not being able to c_p_a() there) is valid behavior and not interesting to report. Remove it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 100.0% arch/x86/mm/ or something much more complex like commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 15.3% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ where that latter example is an example of significant work in some individual fs/*/ subdirectories (like the patches to reiserfs accounting for 7.6% of the whole), but then discounting those individual filesystems, there's also 15.3% other "random" things that weren't worth reporting on their oen left over under fs/ in general (either in that directory itself, or in subdirectories of fs/ that didn't have enough changes to be reported individually). I'd like to stress that the "15.3% fs/" mentioned above is the stuff that is under fs/ but that was _not_ significant enough to report on its own. So the above does _not_ mean that 15.3% of the work was under fs/ per se, because that 15.3% does *not* include the already-reported 7.6% of afs, 7.6% of fuse etc. If you want to enable "cumulative" directory statistics, you can use the "--cumulative" flag, which adds up percentages recursively even when they have been already reported for a sub-directory. That cumulative output is disabled if *all* of the changes in one subdirectory come from a deeper subdirectory, to avoid repeating subdirectories all the way to the root. For an example of the cumulative reporting, the above commit becomes commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 61.5% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ in which the commit percentages now obviously add up to much more than 100%: now the changes that were already reported for the sub-directories under fs/ are then cumulatively included in the whole percentage of fs/ (ie now shows 61.5% as opposed to the 15.3% without the cumulative reporting). The default reporting limit has been arbitrarily set at 3%, which seems to be a pretty good cut-off, but you can specify the cut-off manually by giving it as an option parameter (eg "--dirstat=5" makes the cut-off be at 5% instead) NOTE! The percentages are purely about the total lines added and removed, not anything smarter (or dumber) than that. Also note that you should not generally expect things to add up to 100%: not only does it round down, we don't report leftover scraps (they add up to the top-level change count, but we don't even bother reporting that, it only reports subdirectories). Quite frankly, as a top-level manager this is really convenient for me, but it's going to be very boring for git itself since there are few subdirectories. Also, don't expect things to make tons of sense if you combine this with "-M" and there are cross-directory renames etc. But even for git itself, you can get some fun statistics. Try out git log --dirstat and see the occasional mentions of things like Documentation/, git-gui/, gitweb/ and gitk-git/. Or try out something like git diff --dirstat v1.5.0..v1.5.4 which does kind of git an overview that shows *something*. But in general, the output is more exciting for big projects with deeper structure, and doing a git diff --dirstat v2.6.24..v2.6.25-rc1 on the kernel is what I actually wrote this for! Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 05:26:31 +08:00
sources++;
} else {
this = f->changed;
Add "--dirstat" for some directory statistics This adds a new form of overview diffstat output, doing something that I have occasionally ended up doing manually (and badly, because it's actually pretty nasty to do), and that I think is very useful for an project like the kernel that has a fairly deep and well-separated directory structure with semantic meaning. What I mean by that is that it's often interesting to see exactly which sub-directories are impacted by a patch, and to what degree - even if you don't perhaps care so much about the individual files themselves. What makes the concept more interesting is that the "impact" is often hierarchical: in the kernel, for example, something could either have a very localized impact to "fs/ext3/" and then it's interesting to see that such a patch changes mostly that subdirectory, but you could have another patch that changes some generic VFS-layer issue which affects _many_ subdirectories that are all under "fs/", but none - or perhaps just a couple of them - of the individual filesystems are interesting in themselves. So what commonly happens is that you may have big changes in a specific sub-subdirectory, but still also significant separate changes to the subdirectory leading up to that - maybe you have significant VFS-level changes, but *also* changes under that VFS layer in the NFS-specific directories, for example. In that case, you do want the low-level parts that are significant to show up, but then the insignificant ones should show up as under the more generic top-level directory. This patch shows all of that with "--dirstat". The output can be either something simple like commit 81772fe... Author: Thomas Gleixner <tglx@linutronix.de> Date: Sun Feb 10 23:57:36 2008 +0100 x86: remove over noisy debug printk pageattr-test.c contains a noisy debug printk that people reported. The condition under which it prints (randomly tapping into a mem_map[] hole and not being able to c_p_a() there) is valid behavior and not interesting to report. Remove it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 100.0% arch/x86/mm/ or something much more complex like commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 15.3% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ where that latter example is an example of significant work in some individual fs/*/ subdirectories (like the patches to reiserfs accounting for 7.6% of the whole), but then discounting those individual filesystems, there's also 15.3% other "random" things that weren't worth reporting on their oen left over under fs/ in general (either in that directory itself, or in subdirectories of fs/ that didn't have enough changes to be reported individually). I'd like to stress that the "15.3% fs/" mentioned above is the stuff that is under fs/ but that was _not_ significant enough to report on its own. So the above does _not_ mean that 15.3% of the work was under fs/ per se, because that 15.3% does *not* include the already-reported 7.6% of afs, 7.6% of fuse etc. If you want to enable "cumulative" directory statistics, you can use the "--cumulative" flag, which adds up percentages recursively even when they have been already reported for a sub-directory. That cumulative output is disabled if *all* of the changes in one subdirectory come from a deeper subdirectory, to avoid repeating subdirectories all the way to the root. For an example of the cumulative reporting, the above commit becomes commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 61.5% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ in which the commit percentages now obviously add up to much more than 100%: now the changes that were already reported for the sub-directories under fs/ are then cumulatively included in the whole percentage of fs/ (ie now shows 61.5% as opposed to the 15.3% without the cumulative reporting). The default reporting limit has been arbitrarily set at 3%, which seems to be a pretty good cut-off, but you can specify the cut-off manually by giving it as an option parameter (eg "--dirstat=5" makes the cut-off be at 5% instead) NOTE! The percentages are purely about the total lines added and removed, not anything smarter (or dumber) than that. Also note that you should not generally expect things to add up to 100%: not only does it round down, we don't report leftover scraps (they add up to the top-level change count, but we don't even bother reporting that, it only reports subdirectories). Quite frankly, as a top-level manager this is really convenient for me, but it's going to be very boring for git itself since there are few subdirectories. Also, don't expect things to make tons of sense if you combine this with "-M" and there are cross-directory renames etc. But even for git itself, you can get some fun statistics. Try out git log --dirstat and see the occasional mentions of things like Documentation/, git-gui/, gitweb/ and gitk-git/. Or try out something like git diff --dirstat v1.5.0..v1.5.4 which does kind of git an overview that shows *something*. But in general, the output is more exciting for big projects with deeper structure, and doing a git diff --dirstat v2.6.24..v2.6.25-rc1 on the kernel is what I actually wrote this for! Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 05:26:31 +08:00
dir->files++;
dir->nr--;
sources += 2;
}
this_dir += this;
}
/*
* We don't report dirstat's for
* - the top level
* - or cases where everything came from a single directory
* under this directory (sources == 1).
*/
if (baselen && sources != 1) {
int permille = this_dir * 1000 / changed;
if (permille) {
int percent = permille / 10;
if (percent >= dir->percent) {
fprintf(file, "%4d.%01d%% %.*s\n", percent, permille % 10, baselen, base);
Add "--dirstat" for some directory statistics This adds a new form of overview diffstat output, doing something that I have occasionally ended up doing manually (and badly, because it's actually pretty nasty to do), and that I think is very useful for an project like the kernel that has a fairly deep and well-separated directory structure with semantic meaning. What I mean by that is that it's often interesting to see exactly which sub-directories are impacted by a patch, and to what degree - even if you don't perhaps care so much about the individual files themselves. What makes the concept more interesting is that the "impact" is often hierarchical: in the kernel, for example, something could either have a very localized impact to "fs/ext3/" and then it's interesting to see that such a patch changes mostly that subdirectory, but you could have another patch that changes some generic VFS-layer issue which affects _many_ subdirectories that are all under "fs/", but none - or perhaps just a couple of them - of the individual filesystems are interesting in themselves. So what commonly happens is that you may have big changes in a specific sub-subdirectory, but still also significant separate changes to the subdirectory leading up to that - maybe you have significant VFS-level changes, but *also* changes under that VFS layer in the NFS-specific directories, for example. In that case, you do want the low-level parts that are significant to show up, but then the insignificant ones should show up as under the more generic top-level directory. This patch shows all of that with "--dirstat". The output can be either something simple like commit 81772fe... Author: Thomas Gleixner <tglx@linutronix.de> Date: Sun Feb 10 23:57:36 2008 +0100 x86: remove over noisy debug printk pageattr-test.c contains a noisy debug printk that people reported. The condition under which it prints (randomly tapping into a mem_map[] hole and not being able to c_p_a() there) is valid behavior and not interesting to report. Remove it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 100.0% arch/x86/mm/ or something much more complex like commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 15.3% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ where that latter example is an example of significant work in some individual fs/*/ subdirectories (like the patches to reiserfs accounting for 7.6% of the whole), but then discounting those individual filesystems, there's also 15.3% other "random" things that weren't worth reporting on their oen left over under fs/ in general (either in that directory itself, or in subdirectories of fs/ that didn't have enough changes to be reported individually). I'd like to stress that the "15.3% fs/" mentioned above is the stuff that is under fs/ but that was _not_ significant enough to report on its own. So the above does _not_ mean that 15.3% of the work was under fs/ per se, because that 15.3% does *not* include the already-reported 7.6% of afs, 7.6% of fuse etc. If you want to enable "cumulative" directory statistics, you can use the "--cumulative" flag, which adds up percentages recursively even when they have been already reported for a sub-directory. That cumulative output is disabled if *all* of the changes in one subdirectory come from a deeper subdirectory, to avoid repeating subdirectories all the way to the root. For an example of the cumulative reporting, the above commit becomes commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 61.5% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ in which the commit percentages now obviously add up to much more than 100%: now the changes that were already reported for the sub-directories under fs/ are then cumulatively included in the whole percentage of fs/ (ie now shows 61.5% as opposed to the 15.3% without the cumulative reporting). The default reporting limit has been arbitrarily set at 3%, which seems to be a pretty good cut-off, but you can specify the cut-off manually by giving it as an option parameter (eg "--dirstat=5" makes the cut-off be at 5% instead) NOTE! The percentages are purely about the total lines added and removed, not anything smarter (or dumber) than that. Also note that you should not generally expect things to add up to 100%: not only does it round down, we don't report leftover scraps (they add up to the top-level change count, but we don't even bother reporting that, it only reports subdirectories). Quite frankly, as a top-level manager this is really convenient for me, but it's going to be very boring for git itself since there are few subdirectories. Also, don't expect things to make tons of sense if you combine this with "-M" and there are cross-directory renames etc. But even for git itself, you can get some fun statistics. Try out git log --dirstat and see the occasional mentions of things like Documentation/, git-gui/, gitweb/ and gitk-git/. Or try out something like git diff --dirstat v1.5.0..v1.5.4 which does kind of git an overview that shows *something*. But in general, the output is more exciting for big projects with deeper structure, and doing a git diff --dirstat v2.6.24..v2.6.25-rc1 on the kernel is what I actually wrote this for! Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 05:26:31 +08:00
if (!dir->cumulative)
return 0;
}
}
}
return this_dir;
}
Fix '--dirstat' with cross-directory renaming The dirstat code depends on the fact that we always generate diffs with the names sorted, since it then just does a single-pass walk-over of the sorted list of names and how many changes there were. The sorting means that all files are nicely grouped by directory. That all works fine. Except when we have rename detection, and suddenly the nicely sorted list of pathnames isn't all that sorted at all. And now the single-pass dirstat walk gets all confused, and you can get results like this: [torvalds@nehalem linux]$ git diff --dirstat=2 -M v2.6.27-rc4..v2.6.27-rc5 3.0% arch/powerpc/configs/ 6.8% arch/arm/configs/ 2.7% arch/powerpc/configs/ 4.2% arch/arm/configs/ 5.6% arch/powerpc/configs/ 8.4% arch/arm/configs/ 5.5% arch/powerpc/configs/ 23.3% arch/arm/configs/ 8.6% arch/powerpc/configs/ 4.0% arch/ 4.4% drivers/usb/musb/ 4.0% drivers/watchdog/ 7.6% drivers/ 3.5% fs/ The trivial fix is to add a sorting pass, fixing it to: [torvalds@nehalem linux]$ git diff --dirstat=2 -M v2.6.27-rc4..v2.6.27-rc5 43.0% arch/arm/configs/ 25.5% arch/powerpc/configs/ 5.3% arch/ 4.4% drivers/usb/musb/ 4.0% drivers/watchdog/ 7.6% drivers/ 3.5% fs/ Spot the difference. In case anybody wonders: it's because of a ton of renames from {include/asm-blackfin => arch/blackfin/include/asm} that just totally messed up the file ordering in between arch/arm and arch/powerpc. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-08-29 07:19:08 +08:00
static int dirstat_compare(const void *_a, const void *_b)
{
const struct dirstat_file *a = _a;
const struct dirstat_file *b = _b;
return strcmp(a->name, b->name);
}
static void show_dirstat(struct diff_options *options)
Add "--dirstat" for some directory statistics This adds a new form of overview diffstat output, doing something that I have occasionally ended up doing manually (and badly, because it's actually pretty nasty to do), and that I think is very useful for an project like the kernel that has a fairly deep and well-separated directory structure with semantic meaning. What I mean by that is that it's often interesting to see exactly which sub-directories are impacted by a patch, and to what degree - even if you don't perhaps care so much about the individual files themselves. What makes the concept more interesting is that the "impact" is often hierarchical: in the kernel, for example, something could either have a very localized impact to "fs/ext3/" and then it's interesting to see that such a patch changes mostly that subdirectory, but you could have another patch that changes some generic VFS-layer issue which affects _many_ subdirectories that are all under "fs/", but none - or perhaps just a couple of them - of the individual filesystems are interesting in themselves. So what commonly happens is that you may have big changes in a specific sub-subdirectory, but still also significant separate changes to the subdirectory leading up to that - maybe you have significant VFS-level changes, but *also* changes under that VFS layer in the NFS-specific directories, for example. In that case, you do want the low-level parts that are significant to show up, but then the insignificant ones should show up as under the more generic top-level directory. This patch shows all of that with "--dirstat". The output can be either something simple like commit 81772fe... Author: Thomas Gleixner <tglx@linutronix.de> Date: Sun Feb 10 23:57:36 2008 +0100 x86: remove over noisy debug printk pageattr-test.c contains a noisy debug printk that people reported. The condition under which it prints (randomly tapping into a mem_map[] hole and not being able to c_p_a() there) is valid behavior and not interesting to report. Remove it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 100.0% arch/x86/mm/ or something much more complex like commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 15.3% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ where that latter example is an example of significant work in some individual fs/*/ subdirectories (like the patches to reiserfs accounting for 7.6% of the whole), but then discounting those individual filesystems, there's also 15.3% other "random" things that weren't worth reporting on their oen left over under fs/ in general (either in that directory itself, or in subdirectories of fs/ that didn't have enough changes to be reported individually). I'd like to stress that the "15.3% fs/" mentioned above is the stuff that is under fs/ but that was _not_ significant enough to report on its own. So the above does _not_ mean that 15.3% of the work was under fs/ per se, because that 15.3% does *not* include the already-reported 7.6% of afs, 7.6% of fuse etc. If you want to enable "cumulative" directory statistics, you can use the "--cumulative" flag, which adds up percentages recursively even when they have been already reported for a sub-directory. That cumulative output is disabled if *all* of the changes in one subdirectory come from a deeper subdirectory, to avoid repeating subdirectories all the way to the root. For an example of the cumulative reporting, the above commit becomes commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 61.5% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ in which the commit percentages now obviously add up to much more than 100%: now the changes that were already reported for the sub-directories under fs/ are then cumulatively included in the whole percentage of fs/ (ie now shows 61.5% as opposed to the 15.3% without the cumulative reporting). The default reporting limit has been arbitrarily set at 3%, which seems to be a pretty good cut-off, but you can specify the cut-off manually by giving it as an option parameter (eg "--dirstat=5" makes the cut-off be at 5% instead) NOTE! The percentages are purely about the total lines added and removed, not anything smarter (or dumber) than that. Also note that you should not generally expect things to add up to 100%: not only does it round down, we don't report leftover scraps (they add up to the top-level change count, but we don't even bother reporting that, it only reports subdirectories). Quite frankly, as a top-level manager this is really convenient for me, but it's going to be very boring for git itself since there are few subdirectories. Also, don't expect things to make tons of sense if you combine this with "-M" and there are cross-directory renames etc. But even for git itself, you can get some fun statistics. Try out git log --dirstat and see the occasional mentions of things like Documentation/, git-gui/, gitweb/ and gitk-git/. Or try out something like git diff --dirstat v1.5.0..v1.5.4 which does kind of git an overview that shows *something*. But in general, the output is more exciting for big projects with deeper structure, and doing a git diff --dirstat v2.6.24..v2.6.25-rc1 on the kernel is what I actually wrote this for! Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 05:26:31 +08:00
{
int i;
unsigned long changed;
struct dirstat_dir dir;
struct diff_queue_struct *q = &diff_queued_diff;
dir.files = NULL;
dir.alloc = 0;
dir.nr = 0;
dir.percent = options->dirstat_percent;
dir.cumulative = DIFF_OPT_TST(options, DIRSTAT_CUMULATIVE);
Add "--dirstat" for some directory statistics This adds a new form of overview diffstat output, doing something that I have occasionally ended up doing manually (and badly, because it's actually pretty nasty to do), and that I think is very useful for an project like the kernel that has a fairly deep and well-separated directory structure with semantic meaning. What I mean by that is that it's often interesting to see exactly which sub-directories are impacted by a patch, and to what degree - even if you don't perhaps care so much about the individual files themselves. What makes the concept more interesting is that the "impact" is often hierarchical: in the kernel, for example, something could either have a very localized impact to "fs/ext3/" and then it's interesting to see that such a patch changes mostly that subdirectory, but you could have another patch that changes some generic VFS-layer issue which affects _many_ subdirectories that are all under "fs/", but none - or perhaps just a couple of them - of the individual filesystems are interesting in themselves. So what commonly happens is that you may have big changes in a specific sub-subdirectory, but still also significant separate changes to the subdirectory leading up to that - maybe you have significant VFS-level changes, but *also* changes under that VFS layer in the NFS-specific directories, for example. In that case, you do want the low-level parts that are significant to show up, but then the insignificant ones should show up as under the more generic top-level directory. This patch shows all of that with "--dirstat". The output can be either something simple like commit 81772fe... Author: Thomas Gleixner <tglx@linutronix.de> Date: Sun Feb 10 23:57:36 2008 +0100 x86: remove over noisy debug printk pageattr-test.c contains a noisy debug printk that people reported. The condition under which it prints (randomly tapping into a mem_map[] hole and not being able to c_p_a() there) is valid behavior and not interesting to report. Remove it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 100.0% arch/x86/mm/ or something much more complex like commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 15.3% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ where that latter example is an example of significant work in some individual fs/*/ subdirectories (like the patches to reiserfs accounting for 7.6% of the whole), but then discounting those individual filesystems, there's also 15.3% other "random" things that weren't worth reporting on their oen left over under fs/ in general (either in that directory itself, or in subdirectories of fs/ that didn't have enough changes to be reported individually). I'd like to stress that the "15.3% fs/" mentioned above is the stuff that is under fs/ but that was _not_ significant enough to report on its own. So the above does _not_ mean that 15.3% of the work was under fs/ per se, because that 15.3% does *not* include the already-reported 7.6% of afs, 7.6% of fuse etc. If you want to enable "cumulative" directory statistics, you can use the "--cumulative" flag, which adds up percentages recursively even when they have been already reported for a sub-directory. That cumulative output is disabled if *all* of the changes in one subdirectory come from a deeper subdirectory, to avoid repeating subdirectories all the way to the root. For an example of the cumulative reporting, the above commit becomes commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 61.5% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ in which the commit percentages now obviously add up to much more than 100%: now the changes that were already reported for the sub-directories under fs/ are then cumulatively included in the whole percentage of fs/ (ie now shows 61.5% as opposed to the 15.3% without the cumulative reporting). The default reporting limit has been arbitrarily set at 3%, which seems to be a pretty good cut-off, but you can specify the cut-off manually by giving it as an option parameter (eg "--dirstat=5" makes the cut-off be at 5% instead) NOTE! The percentages are purely about the total lines added and removed, not anything smarter (or dumber) than that. Also note that you should not generally expect things to add up to 100%: not only does it round down, we don't report leftover scraps (they add up to the top-level change count, but we don't even bother reporting that, it only reports subdirectories). Quite frankly, as a top-level manager this is really convenient for me, but it's going to be very boring for git itself since there are few subdirectories. Also, don't expect things to make tons of sense if you combine this with "-M" and there are cross-directory renames etc. But even for git itself, you can get some fun statistics. Try out git log --dirstat and see the occasional mentions of things like Documentation/, git-gui/, gitweb/ and gitk-git/. Or try out something like git diff --dirstat v1.5.0..v1.5.4 which does kind of git an overview that shows *something*. But in general, the output is more exciting for big projects with deeper structure, and doing a git diff --dirstat v2.6.24..v2.6.25-rc1 on the kernel is what I actually wrote this for! Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 05:26:31 +08:00
changed = 0;
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
const char *name;
unsigned long copied, added, damage;
name = p->one->path ? p->one->path : p->two->path;
if (DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two)) {
diff_populate_filespec(p->one, 0);
diff_populate_filespec(p->two, 0);
diffcore_count_changes(p->one, p->two, NULL, NULL, 0,
&copied, &added);
diff_free_filespec_data(p->one);
diff_free_filespec_data(p->two);
} else if (DIFF_FILE_VALID(p->one)) {
diff_populate_filespec(p->one, 1);
copied = added = 0;
diff_free_filespec_data(p->one);
} else if (DIFF_FILE_VALID(p->two)) {
diff_populate_filespec(p->two, 1);
copied = 0;
added = p->two->size;
diff_free_filespec_data(p->two);
} else
continue;
/*
* Original minus copied is the removed material,
* added is the new material. They are both damages
* made to the preimage. In --dirstat-by-file mode, count
* damaged files, not damaged lines. This is done by
* counting only a single damaged line per file.
*/
damage = (p->one->size - copied) + added;
if (DIFF_OPT_TST(options, DIRSTAT_BY_FILE) && damage > 0)
damage = 1;
ALLOC_GROW(dir.files, dir.nr + 1, dir.alloc);
dir.files[dir.nr].name = name;
dir.files[dir.nr].changed = damage;
changed += damage;
dir.nr++;
Add "--dirstat" for some directory statistics This adds a new form of overview diffstat output, doing something that I have occasionally ended up doing manually (and badly, because it's actually pretty nasty to do), and that I think is very useful for an project like the kernel that has a fairly deep and well-separated directory structure with semantic meaning. What I mean by that is that it's often interesting to see exactly which sub-directories are impacted by a patch, and to what degree - even if you don't perhaps care so much about the individual files themselves. What makes the concept more interesting is that the "impact" is often hierarchical: in the kernel, for example, something could either have a very localized impact to "fs/ext3/" and then it's interesting to see that such a patch changes mostly that subdirectory, but you could have another patch that changes some generic VFS-layer issue which affects _many_ subdirectories that are all under "fs/", but none - or perhaps just a couple of them - of the individual filesystems are interesting in themselves. So what commonly happens is that you may have big changes in a specific sub-subdirectory, but still also significant separate changes to the subdirectory leading up to that - maybe you have significant VFS-level changes, but *also* changes under that VFS layer in the NFS-specific directories, for example. In that case, you do want the low-level parts that are significant to show up, but then the insignificant ones should show up as under the more generic top-level directory. This patch shows all of that with "--dirstat". The output can be either something simple like commit 81772fe... Author: Thomas Gleixner <tglx@linutronix.de> Date: Sun Feb 10 23:57:36 2008 +0100 x86: remove over noisy debug printk pageattr-test.c contains a noisy debug printk that people reported. The condition under which it prints (randomly tapping into a mem_map[] hole and not being able to c_p_a() there) is valid behavior and not interesting to report. Remove it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 100.0% arch/x86/mm/ or something much more complex like commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 15.3% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ where that latter example is an example of significant work in some individual fs/*/ subdirectories (like the patches to reiserfs accounting for 7.6% of the whole), but then discounting those individual filesystems, there's also 15.3% other "random" things that weren't worth reporting on their oen left over under fs/ in general (either in that directory itself, or in subdirectories of fs/ that didn't have enough changes to be reported individually). I'd like to stress that the "15.3% fs/" mentioned above is the stuff that is under fs/ but that was _not_ significant enough to report on its own. So the above does _not_ mean that 15.3% of the work was under fs/ per se, because that 15.3% does *not* include the already-reported 7.6% of afs, 7.6% of fuse etc. If you want to enable "cumulative" directory statistics, you can use the "--cumulative" flag, which adds up percentages recursively even when they have been already reported for a sub-directory. That cumulative output is disabled if *all* of the changes in one subdirectory come from a deeper subdirectory, to avoid repeating subdirectories all the way to the root. For an example of the cumulative reporting, the above commit becomes commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 61.5% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ in which the commit percentages now obviously add up to much more than 100%: now the changes that were already reported for the sub-directories under fs/ are then cumulatively included in the whole percentage of fs/ (ie now shows 61.5% as opposed to the 15.3% without the cumulative reporting). The default reporting limit has been arbitrarily set at 3%, which seems to be a pretty good cut-off, but you can specify the cut-off manually by giving it as an option parameter (eg "--dirstat=5" makes the cut-off be at 5% instead) NOTE! The percentages are purely about the total lines added and removed, not anything smarter (or dumber) than that. Also note that you should not generally expect things to add up to 100%: not only does it round down, we don't report leftover scraps (they add up to the top-level change count, but we don't even bother reporting that, it only reports subdirectories). Quite frankly, as a top-level manager this is really convenient for me, but it's going to be very boring for git itself since there are few subdirectories. Also, don't expect things to make tons of sense if you combine this with "-M" and there are cross-directory renames etc. But even for git itself, you can get some fun statistics. Try out git log --dirstat and see the occasional mentions of things like Documentation/, git-gui/, gitweb/ and gitk-git/. Or try out something like git diff --dirstat v1.5.0..v1.5.4 which does kind of git an overview that shows *something*. But in general, the output is more exciting for big projects with deeper structure, and doing a git diff --dirstat v2.6.24..v2.6.25-rc1 on the kernel is what I actually wrote this for! Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 05:26:31 +08:00
}
/* This can happen even with many files, if everything was renames */
if (!changed)
return;
/* Show all directories with more than x% of the changes */
Fix '--dirstat' with cross-directory renaming The dirstat code depends on the fact that we always generate diffs with the names sorted, since it then just does a single-pass walk-over of the sorted list of names and how many changes there were. The sorting means that all files are nicely grouped by directory. That all works fine. Except when we have rename detection, and suddenly the nicely sorted list of pathnames isn't all that sorted at all. And now the single-pass dirstat walk gets all confused, and you can get results like this: [torvalds@nehalem linux]$ git diff --dirstat=2 -M v2.6.27-rc4..v2.6.27-rc5 3.0% arch/powerpc/configs/ 6.8% arch/arm/configs/ 2.7% arch/powerpc/configs/ 4.2% arch/arm/configs/ 5.6% arch/powerpc/configs/ 8.4% arch/arm/configs/ 5.5% arch/powerpc/configs/ 23.3% arch/arm/configs/ 8.6% arch/powerpc/configs/ 4.0% arch/ 4.4% drivers/usb/musb/ 4.0% drivers/watchdog/ 7.6% drivers/ 3.5% fs/ The trivial fix is to add a sorting pass, fixing it to: [torvalds@nehalem linux]$ git diff --dirstat=2 -M v2.6.27-rc4..v2.6.27-rc5 43.0% arch/arm/configs/ 25.5% arch/powerpc/configs/ 5.3% arch/ 4.4% drivers/usb/musb/ 4.0% drivers/watchdog/ 7.6% drivers/ 3.5% fs/ Spot the difference. In case anybody wonders: it's because of a ton of renames from {include/asm-blackfin => arch/blackfin/include/asm} that just totally messed up the file ordering in between arch/arm and arch/powerpc. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-08-29 07:19:08 +08:00
qsort(dir.files, dir.nr, sizeof(dir.files[0]), dirstat_compare);
gather_dirstat(options->file, &dir, changed, "", 0);
Add "--dirstat" for some directory statistics This adds a new form of overview diffstat output, doing something that I have occasionally ended up doing manually (and badly, because it's actually pretty nasty to do), and that I think is very useful for an project like the kernel that has a fairly deep and well-separated directory structure with semantic meaning. What I mean by that is that it's often interesting to see exactly which sub-directories are impacted by a patch, and to what degree - even if you don't perhaps care so much about the individual files themselves. What makes the concept more interesting is that the "impact" is often hierarchical: in the kernel, for example, something could either have a very localized impact to "fs/ext3/" and then it's interesting to see that such a patch changes mostly that subdirectory, but you could have another patch that changes some generic VFS-layer issue which affects _many_ subdirectories that are all under "fs/", but none - or perhaps just a couple of them - of the individual filesystems are interesting in themselves. So what commonly happens is that you may have big changes in a specific sub-subdirectory, but still also significant separate changes to the subdirectory leading up to that - maybe you have significant VFS-level changes, but *also* changes under that VFS layer in the NFS-specific directories, for example. In that case, you do want the low-level parts that are significant to show up, but then the insignificant ones should show up as under the more generic top-level directory. This patch shows all of that with "--dirstat". The output can be either something simple like commit 81772fe... Author: Thomas Gleixner <tglx@linutronix.de> Date: Sun Feb 10 23:57:36 2008 +0100 x86: remove over noisy debug printk pageattr-test.c contains a noisy debug printk that people reported. The condition under which it prints (randomly tapping into a mem_map[] hole and not being able to c_p_a() there) is valid behavior and not interesting to report. Remove it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 100.0% arch/x86/mm/ or something much more complex like commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 15.3% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ where that latter example is an example of significant work in some individual fs/*/ subdirectories (like the patches to reiserfs accounting for 7.6% of the whole), but then discounting those individual filesystems, there's also 15.3% other "random" things that weren't worth reporting on their oen left over under fs/ in general (either in that directory itself, or in subdirectories of fs/ that didn't have enough changes to be reported individually). I'd like to stress that the "15.3% fs/" mentioned above is the stuff that is under fs/ but that was _not_ significant enough to report on its own. So the above does _not_ mean that 15.3% of the work was under fs/ per se, because that 15.3% does *not* include the already-reported 7.6% of afs, 7.6% of fuse etc. If you want to enable "cumulative" directory statistics, you can use the "--cumulative" flag, which adds up percentages recursively even when they have been already reported for a sub-directory. That cumulative output is disabled if *all* of the changes in one subdirectory come from a deeper subdirectory, to avoid repeating subdirectories all the way to the root. For an example of the cumulative reporting, the above commit becomes commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 61.5% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ in which the commit percentages now obviously add up to much more than 100%: now the changes that were already reported for the sub-directories under fs/ are then cumulatively included in the whole percentage of fs/ (ie now shows 61.5% as opposed to the 15.3% without the cumulative reporting). The default reporting limit has been arbitrarily set at 3%, which seems to be a pretty good cut-off, but you can specify the cut-off manually by giving it as an option parameter (eg "--dirstat=5" makes the cut-off be at 5% instead) NOTE! The percentages are purely about the total lines added and removed, not anything smarter (or dumber) than that. Also note that you should not generally expect things to add up to 100%: not only does it round down, we don't report leftover scraps (they add up to the top-level change count, but we don't even bother reporting that, it only reports subdirectories). Quite frankly, as a top-level manager this is really convenient for me, but it's going to be very boring for git itself since there are few subdirectories. Also, don't expect things to make tons of sense if you combine this with "-M" and there are cross-directory renames etc. But even for git itself, you can get some fun statistics. Try out git log --dirstat and see the occasional mentions of things like Documentation/, git-gui/, gitweb/ and gitk-git/. Or try out something like git diff --dirstat v1.5.0..v1.5.4 which does kind of git an overview that shows *something*. But in general, the output is more exciting for big projects with deeper structure, and doing a git diff --dirstat v2.6.24..v2.6.25-rc1 on the kernel is what I actually wrote this for! Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 05:26:31 +08:00
}
static void free_diffstat_info(struct diffstat_t *diffstat)
{
int i;
for (i = 0; i < diffstat->nr; i++) {
struct diffstat_file *f = diffstat->files[i];
if (f->name != f->print_name)
free(f->print_name);
free(f->name);
free(f->from_name);
free(f);
}
free(diffstat->files);
}
struct checkdiff_t {
const char *filename;
int lineno;
struct diff_options *o;
unsigned ws_rule;
unsigned status;
};
static int is_conflict_marker(const char *line, unsigned long len)
{
char firstchar;
int cnt;
if (len < 8)
return 0;
firstchar = line[0];
switch (firstchar) {
case '=': case '>': case '<':
break;
default:
return 0;
}
for (cnt = 1; cnt < 7; cnt++)
if (line[cnt] != firstchar)
return 0;
/* line[0] thru line[6] are same as firstchar */
if (firstchar == '=') {
/* divider between ours and theirs? */
if (len != 8 || line[7] != '\n')
return 0;
} else if (len < 8 || !isspace(line[7])) {
/* not divider before ours nor after theirs */
return 0;
}
return 1;
}
static void checkdiff_consume(void *priv, char *line, unsigned long len)
{
struct checkdiff_t *data = priv;
int color_diff = DIFF_OPT_TST(data->o, COLOR_DIFF);
const char *ws = diff_get_color(color_diff, DIFF_WHITESPACE);
const char *reset = diff_get_color(color_diff, DIFF_RESET);
const char *set = diff_get_color(color_diff, DIFF_FILE_NEW);
char *err;
if (line[0] == '+') {
unsigned bad;
data->lineno++;
if (is_conflict_marker(line + 1, len - 1)) {
data->status |= 1;
fprintf(data->o->file,
"%s:%d: leftover conflict marker\n",
data->filename, data->lineno);
}
bad = ws_check(line + 1, len - 1, data->ws_rule);
if (!bad)
return;
data->status |= bad;
err = whitespace_error_string(bad);
fprintf(data->o->file, "%s:%d: %s.\n",
data->filename, data->lineno, err);
free(err);
emit_line(data->o->file, set, reset, line, 1);
ws_check_emit(line + 1, len - 1, data->ws_rule,
data->o->file, set, reset, ws);
} else if (line[0] == ' ') {
data->lineno++;
} else if (line[0] == '@') {
char *plus = strchr(line, '+');
if (plus)
data->lineno = strtol(plus, NULL, 10) - 1;
else
die("invalid diff");
}
}
static unsigned char *deflate_it(char *data,
unsigned long size,
unsigned long *result_size)
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
{
int bound;
unsigned char *deflated;
z_stream stream;
memset(&stream, 0, sizeof(stream));
deflateInit(&stream, zlib_compression_level);
bound = deflateBound(&stream, size);
deflated = xmalloc(bound);
stream.next_out = deflated;
stream.avail_out = bound;
stream.next_in = (unsigned char *)data;
stream.avail_in = size;
while (deflate(&stream, Z_FINISH) == Z_OK)
; /* nothing */
deflateEnd(&stream);
*result_size = stream.total_out;
return deflated;
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
}
static void emit_binary_diff_body(FILE *file, mmfile_t *one, mmfile_t *two)
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
{
void *cp;
void *delta;
void *deflated;
void *data;
unsigned long orig_size;
unsigned long delta_size;
unsigned long deflate_size;
unsigned long data_size;
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
/* We could do deflated delta, or we could do just deflated two,
* whichever is smaller.
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
*/
delta = NULL;
deflated = deflate_it(two->ptr, two->size, &deflate_size);
if (one->size && two->size) {
delta = diff_delta(one->ptr, one->size,
two->ptr, two->size,
&delta_size, deflate_size);
if (delta) {
void *to_free = delta;
orig_size = delta_size;
delta = deflate_it(delta, delta_size, &delta_size);
free(to_free);
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
}
}
if (delta && delta_size < deflate_size) {
fprintf(file, "delta %lu\n", orig_size);
free(deflated);
data = delta;
data_size = delta_size;
}
else {
fprintf(file, "literal %lu\n", two->size);
free(delta);
data = deflated;
data_size = deflate_size;
}
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
/* emit data encoded in base85 */
cp = data;
while (data_size) {
int bytes = (52 < data_size) ? 52 : data_size;
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
char line[70];
data_size -= bytes;
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
if (bytes <= 26)
line[0] = bytes + 'A' - 1;
else
line[0] = bytes - 26 + 'a' - 1;
encode_85(line + 1, cp, bytes);
cp = (char *) cp + bytes;
fputs(line, file);
fputc('\n', file);
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
}
fprintf(file, "\n");
free(data);
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
}
static void emit_binary_diff(FILE *file, mmfile_t *one, mmfile_t *two)
{
fprintf(file, "GIT binary patch\n");
emit_binary_diff_body(file, one, two);
emit_binary_diff_body(file, two, one);
}
static void diff_filespec_load_driver(struct diff_filespec *one)
{
diff: introduce diff.<driver>.binary The "diff" gitattribute is somewhat overloaded right now. It can say one of three things: 1. this file is definitely binary, or definitely not (i.e., diff or !diff) 2. this file should use an external diff engine (i.e., diff=foo, diff.foo.command = custom-script) 3. this file should use particular funcname patterns (i.e., diff=foo, diff.foo.(x?)funcname = some-regex) Most of the time, there is no conflict between these uses, since using one implies that the other is irrelevant (e.g., an external diff engine will decide for itself whether the file is binary). However, there is at least one conflicting situation: there is no way to say "use the regular rules to determine whether this file is binary, but if we do diff it textually, use this funcname pattern." That is, currently setting diff=foo indicates that the file is definitely text. This patch introduces a "binary" config option for a diff driver, so that one can explicitly set diff.foo.binary. We default this value to "don't know". That is, setting a diff attribute to "foo" and using "diff.foo.funcname" will have no effect on the binaryness of a file. To get the current behavior, one can set diff.foo.binary to true. This patch also has one additional advantage: it cleans up the interface to the userdiff code a bit. Before, calling code had to know more about whether attributes were false, true, or unset to determine binaryness. Now that binaryness is a property of a driver, we can represent these situations just by passing back a driver struct. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-06 05:43:36 +08:00
if (!one->driver)
one->driver = userdiff_find_by_path(one->path);
if (!one->driver)
one->driver = userdiff_find_by_name("default");
}
int diff_filespec_is_binary(struct diff_filespec *one)
{
diff: introduce diff.<driver>.binary The "diff" gitattribute is somewhat overloaded right now. It can say one of three things: 1. this file is definitely binary, or definitely not (i.e., diff or !diff) 2. this file should use an external diff engine (i.e., diff=foo, diff.foo.command = custom-script) 3. this file should use particular funcname patterns (i.e., diff=foo, diff.foo.(x?)funcname = some-regex) Most of the time, there is no conflict between these uses, since using one implies that the other is irrelevant (e.g., an external diff engine will decide for itself whether the file is binary). However, there is at least one conflicting situation: there is no way to say "use the regular rules to determine whether this file is binary, but if we do diff it textually, use this funcname pattern." That is, currently setting diff=foo indicates that the file is definitely text. This patch introduces a "binary" config option for a diff driver, so that one can explicitly set diff.foo.binary. We default this value to "don't know". That is, setting a diff attribute to "foo" and using "diff.foo.funcname" will have no effect on the binaryness of a file. To get the current behavior, one can set diff.foo.binary to true. This patch also has one additional advantage: it cleans up the interface to the userdiff code a bit. Before, calling code had to know more about whether attributes were false, true, or unset to determine binaryness. Now that binaryness is a property of a driver, we can represent these situations just by passing back a driver struct. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-06 05:43:36 +08:00
if (one->is_binary == -1) {
diff_filespec_load_driver(one);
if (one->driver->binary != -1)
one->is_binary = one->driver->binary;
else {
if (!one->data && DIFF_FILE_VALID(one))
diff_populate_filespec(one, 0);
if (one->data)
one->is_binary = buffer_is_binary(one->data,
one->size);
if (one->is_binary == -1)
one->is_binary = 0;
}
}
return one->is_binary;
}
static const struct userdiff_funcname *diff_funcname_pattern(struct diff_filespec *one)
{
diff: introduce diff.<driver>.binary The "diff" gitattribute is somewhat overloaded right now. It can say one of three things: 1. this file is definitely binary, or definitely not (i.e., diff or !diff) 2. this file should use an external diff engine (i.e., diff=foo, diff.foo.command = custom-script) 3. this file should use particular funcname patterns (i.e., diff=foo, diff.foo.(x?)funcname = some-regex) Most of the time, there is no conflict between these uses, since using one implies that the other is irrelevant (e.g., an external diff engine will decide for itself whether the file is binary). However, there is at least one conflicting situation: there is no way to say "use the regular rules to determine whether this file is binary, but if we do diff it textually, use this funcname pattern." That is, currently setting diff=foo indicates that the file is definitely text. This patch introduces a "binary" config option for a diff driver, so that one can explicitly set diff.foo.binary. We default this value to "don't know". That is, setting a diff attribute to "foo" and using "diff.foo.funcname" will have no effect on the binaryness of a file. To get the current behavior, one can set diff.foo.binary to true. This patch also has one additional advantage: it cleans up the interface to the userdiff code a bit. Before, calling code had to know more about whether attributes were false, true, or unset to determine binaryness. Now that binaryness is a property of a driver, we can represent these situations just by passing back a driver struct. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-06 05:43:36 +08:00
diff_filespec_load_driver(one);
return one->driver->funcname.pattern ? &one->driver->funcname : NULL;
}
static const char *userdiff_word_regex(struct diff_filespec *one)
{
diff_filespec_load_driver(one);
return one->driver->word_regex;
}
void diff_set_mnemonic_prefix(struct diff_options *options, const char *a, const char *b)
{
if (!options->a_prefix)
options->a_prefix = a;
if (!options->b_prefix)
options->b_prefix = b;
}
static const char *get_textconv(struct diff_filespec *one)
{
if (!DIFF_FILE_VALID(one))
return NULL;
if (!S_ISREG(one->mode))
return NULL;
diff_filespec_load_driver(one);
return one->driver->textconv;
}
static void builtin_diff(const char *name_a,
const char *name_b,
struct diff_filespec *one,
struct diff_filespec *two,
const char *xfrm_msg,
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
struct diff_options *o,
int complete_rewrite)
{
mmfile_t mf1, mf2;
const char *lbl[2];
char *a_one, *b_two;
const char *set = diff_get_color_opt(o, DIFF_METAINFO);
const char *reset = diff_get_color_opt(o, DIFF_RESET);
const char *a_prefix, *b_prefix;
const char *textconv_one = NULL, *textconv_two = NULL;
struct strbuf header = STRBUF_INIT;
if (DIFF_OPT_TST(o, SUBMODULE_LOG) &&
(!one->mode || S_ISGITLINK(one->mode)) &&
(!two->mode || S_ISGITLINK(two->mode))) {
const char *del = diff_get_color_opt(o, DIFF_FILE_OLD);
const char *add = diff_get_color_opt(o, DIFF_FILE_NEW);
show_submodule_summary(o->file, one ? one->path : two->path,
one->sha1, two->sha1, two->dirty_submodule,
del, add, reset);
return;
}
if (DIFF_OPT_TST(o, ALLOW_TEXTCONV)) {
textconv_one = get_textconv(one);
textconv_two = get_textconv(two);
}
diff_set_mnemonic_prefix(o, "a/", "b/");
if (DIFF_OPT_TST(o, REVERSE_DIFF)) {
a_prefix = o->b_prefix;
b_prefix = o->a_prefix;
} else {
a_prefix = o->a_prefix;
b_prefix = o->b_prefix;
}
fix bogus "diff --git" header from "diff --no-index" When "git diff --no-index" is given an absolute pathname, it would generate a diff header with the absolute path prepended by the prefix, like: diff --git a/dev/null b/foo Not only is this nonsensical, and not only does it violate the description of diffs given in git-diff(1), but it would produce broken binary diffs. Unlike text diffs, the binary diffs don't contain the filenames anywhere else, and so "git apply" relies on this header to figure out the filename. This patch just refuses to use an invalid name for anything visible in the diff. Now, this fixes the "git diff --no-index --binary a /dev/null" kind of case (and we'll end up using "a" as the basename), but some other insane cases are impossible to handle. If you do git diff --no-index --binary a /bin/echo you'll still get a patch like diff --git a/a b/bin/echo old mode 100644 new mode 100755 index ... and "git apply" will refuse to apply it for a couple of reasons, and the diff is simply bogus. And that, btw, is no longer a bug, I think. It's impossible to know whethe the user meant for the patch to be a rename or not. And as such, refusing to apply it because you don't know what name you should use is probably _exactly_ the right thing to do! Original problem reported by Imre Deak. Test script and problem description by Jeff King. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-06 03:35:15 +08:00
/* Never use a non-valid filename anywhere if at all possible */
name_a = DIFF_FILE_VALID(one) ? name_a : name_b;
name_b = DIFF_FILE_VALID(two) ? name_b : name_a;
a_one = quote_two(a_prefix, name_a + (*name_a == '/'));
b_two = quote_two(b_prefix, name_b + (*name_b == '/'));
lbl[0] = DIFF_FILE_VALID(one) ? a_one : "/dev/null";
lbl[1] = DIFF_FILE_VALID(two) ? b_two : "/dev/null";
strbuf_addf(&header, "%sdiff --git %s %s%s\n", set, a_one, b_two, reset);
if (lbl[0][0] == '/') {
/* /dev/null */
strbuf_addf(&header, "%snew file mode %06o%s\n", set, two->mode, reset);
if (xfrm_msg && xfrm_msg[0])
strbuf_addf(&header, "%s%s%s\n", set, xfrm_msg, reset);
}
else if (lbl[1][0] == '/') {
strbuf_addf(&header, "%sdeleted file mode %06o%s\n", set, one->mode, reset);
if (xfrm_msg && xfrm_msg[0])
strbuf_addf(&header, "%s%s%s\n", set, xfrm_msg, reset);
}
else {
if (one->mode != two->mode) {
strbuf_addf(&header, "%sold mode %06o%s\n", set, one->mode, reset);
strbuf_addf(&header, "%snew mode %06o%s\n", set, two->mode, reset);
}
if (xfrm_msg && xfrm_msg[0])
strbuf_addf(&header, "%s%s%s\n", set, xfrm_msg, reset);
/*
* we do not run diff between different kind
* of objects.
*/
if ((one->mode ^ two->mode) & S_IFMT)
goto free_ab_and_return;
if (complete_rewrite &&
(textconv_one || !diff_filespec_is_binary(one)) &&
(textconv_two || !diff_filespec_is_binary(two))) {
fprintf(o->file, "%s", header.buf);
strbuf_reset(&header);
emit_rewrite_diff(name_a, name_b, one, two,
textconv_one, textconv_two, o);
o->found_changes = 1;
goto free_ab_and_return;
}
}
if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
die("unable to read files to diff");
if (!DIFF_OPT_TST(o, TEXT) &&
( (diff_filespec_is_binary(one) && !textconv_one) ||
(diff_filespec_is_binary(two) && !textconv_two) )) {
/* Quite common confusing case */
if (mf1.size == mf2.size &&
!memcmp(mf1.ptr, mf2.ptr, mf1.size))
goto free_ab_and_return;
fprintf(o->file, "%s", header.buf);
strbuf_reset(&header);
if (DIFF_OPT_TST(o, BINARY))
emit_binary_diff(o->file, &mf1, &mf2);
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
else
fprintf(o->file, "Binary files %s and %s differ\n",
lbl[0], lbl[1]);
o->found_changes = 1;
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
}
else {
/* Crazy xdl interfaces.. */
const char *diffopts = getenv("GIT_DIFF_OPTS");
xpparam_t xpp;
xdemitconf_t xecfg;
xdemitcb_t ecb;
struct emit_callback ecbdata;
const struct userdiff_funcname *pe;
if (!DIFF_XDL_TST(o, WHITESPACE_FLAGS)) {
fprintf(o->file, "%s", header.buf);
strbuf_reset(&header);
}
if (textconv_one) {
size_t size;
mf1.ptr = run_textconv(textconv_one, one, &size);
if (!mf1.ptr)
die("unable to read files to diff");
mf1.size = size;
}
if (textconv_two) {
size_t size;
mf2.ptr = run_textconv(textconv_two, two, &size);
if (!mf2.ptr)
die("unable to read files to diff");
mf2.size = size;
}
pe = diff_funcname_pattern(one);
if (!pe)
pe = diff_funcname_pattern(two);
memset(&xpp, 0, sizeof(xpp));
memset(&xecfg, 0, sizeof(xecfg));
memset(&ecbdata, 0, sizeof(ecbdata));
ecbdata.label_path = lbl;
ecbdata.color_diff = DIFF_OPT_TST(o, COLOR_DIFF);
ecbdata.found_changesp = &o->found_changes;
ecbdata.ws_rule = whitespace_rule(name_b ? name_b : name_a);
if (ecbdata.ws_rule & WS_BLANK_AT_EOF)
check_blank_at_eof(&mf1, &mf2, &ecbdata);
ecbdata.file = o->file;
ecbdata.header = header.len ? &header : NULL;
xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
xecfg.ctxlen = o->context;
xecfg.interhunkctxlen = o->interhunkcontext;
xecfg.flags = XDL_EMIT_FUNCNAMES;
if (pe)
xdiff_set_find_func(&xecfg, pe->pattern, pe->cflags);
if (!diffopts)
;
else if (!prefixcmp(diffopts, "--unified="))
xecfg.ctxlen = strtoul(diffopts + 10, NULL, 10);
else if (!prefixcmp(diffopts, "-u"))
xecfg.ctxlen = strtoul(diffopts + 2, NULL, 10);
if (DIFF_OPT_TST(o, COLOR_DIFF_WORDS)) {
ecbdata.diff_words =
xcalloc(1, sizeof(struct diff_words_data));
ecbdata.diff_words->file = o->file;
if (!o->word_regex)
o->word_regex = userdiff_word_regex(one);
if (!o->word_regex)
o->word_regex = userdiff_word_regex(two);
if (!o->word_regex)
o->word_regex = diff_word_regex_cfg;
if (o->word_regex) {
ecbdata.diff_words->word_regex = (regex_t *)
xmalloc(sizeof(regex_t));
if (regcomp(ecbdata.diff_words->word_regex,
o->word_regex,
REG_EXTENDED | REG_NEWLINE))
die ("Invalid regular expression: %s",
o->word_regex);
}
}
xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata,
&xpp, &xecfg, &ecb);
if (DIFF_OPT_TST(o, COLOR_DIFF_WORDS))
free_diff_words_data(&ecbdata);
if (textconv_one)
free(mf1.ptr);
if (textconv_two)
free(mf2.ptr);
xdiff_clear_find_func(&xecfg);
}
free_ab_and_return:
strbuf_release(&header);
diff_free_filespec_data(one);
diff_free_filespec_data(two);
free(a_one);
free(b_two);
return;
}
static void builtin_diffstat(const char *name_a, const char *name_b,
struct diff_filespec *one,
struct diff_filespec *two,
struct diffstat_t *diffstat,
struct diff_options *o,
int complete_rewrite)
{
mmfile_t mf1, mf2;
struct diffstat_file *data;
data = diffstat_add(diffstat, name_a, name_b);
if (!one || !two) {
data->is_unmerged = 1;
return;
}
if (diff_filespec_is_binary(one) || diff_filespec_is_binary(two)) {
if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
die("unable to read files to diff");
data->is_binary = 1;
data->added = mf2.size;
data->deleted = mf1.size;
}
else if (complete_rewrite) {
diff_populate_filespec(one, 0);
diff_populate_filespec(two, 0);
data->deleted = count_lines(one->data, one->size);
data->added = count_lines(two->data, two->size);
}
else {
/* Crazy xdl interfaces.. */
xpparam_t xpp;
xdemitconf_t xecfg;
xdemitcb_t ecb;
if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
die("unable to read files to diff");
memset(&xpp, 0, sizeof(xpp));
memset(&xecfg, 0, sizeof(xecfg));
xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
xdi_diff_outf(&mf1, &mf2, diffstat_consume, diffstat,
&xpp, &xecfg, &ecb);
}
diff_free_filespec_data(one);
diff_free_filespec_data(two);
}
static void builtin_checkdiff(const char *name_a, const char *name_b,
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
const char *attr_path,
struct diff_filespec *one,
struct diff_filespec *two,
struct diff_options *o)
{
mmfile_t mf1, mf2;
struct checkdiff_t data;
if (!two)
return;
memset(&data, 0, sizeof(data));
data.filename = name_b ? name_b : name_a;
data.lineno = 0;
data.o = o;
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
data.ws_rule = whitespace_rule(attr_path);
if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
die("unable to read files to diff");
/*
* All the other codepaths check both sides, but not checking
* the "old" side here is deliberate. We are checking the newly
* introduced changes, and as long as the "new" side is text, we
* can and should check what it introduces.
*/
if (diff_filespec_is_binary(two))
goto free_and_return;
else {
/* Crazy xdl interfaces.. */
xpparam_t xpp;
xdemitconf_t xecfg;
xdemitcb_t ecb;
memset(&xpp, 0, sizeof(xpp));
memset(&xecfg, 0, sizeof(xecfg));
xecfg.ctxlen = 1; /* at least one context line */
xpp.flags = XDF_NEED_MINIMAL;
xdi_diff_outf(&mf1, &mf2, checkdiff_consume, &data,
&xpp, &xecfg, &ecb);
if (data.ws_rule & WS_BLANK_AT_EOF) {
struct emit_callback ecbdata;
int blank_at_eof;
ecbdata.ws_rule = data.ws_rule;
check_blank_at_eof(&mf1, &mf2, &ecbdata);
blank_at_eof = ecbdata.blank_at_eof_in_preimage;
if (blank_at_eof) {
static char *err;
if (!err)
err = whitespace_error_string(WS_BLANK_AT_EOF);
fprintf(o->file, "%s:%d: %s.\n",
data.filename, blank_at_eof, err);
data.status = 1; /* report errors */
}
}
}
free_and_return:
diff_free_filespec_data(one);
diff_free_filespec_data(two);
if (data.status)
DIFF_OPT_SET(o, CHECK_FAILED);
}
struct diff_filespec *alloc_filespec(const char *path)
{
int namelen = strlen(path);
struct diff_filespec *spec = xmalloc(sizeof(*spec) + namelen + 1);
memset(spec, 0, sizeof(*spec));
spec->path = (char *)(spec + 1);
memcpy(spec->path, path, namelen+1);
spec->count = 1;
diff: introduce diff.<driver>.binary The "diff" gitattribute is somewhat overloaded right now. It can say one of three things: 1. this file is definitely binary, or definitely not (i.e., diff or !diff) 2. this file should use an external diff engine (i.e., diff=foo, diff.foo.command = custom-script) 3. this file should use particular funcname patterns (i.e., diff=foo, diff.foo.(x?)funcname = some-regex) Most of the time, there is no conflict between these uses, since using one implies that the other is irrelevant (e.g., an external diff engine will decide for itself whether the file is binary). However, there is at least one conflicting situation: there is no way to say "use the regular rules to determine whether this file is binary, but if we do diff it textually, use this funcname pattern." That is, currently setting diff=foo indicates that the file is definitely text. This patch introduces a "binary" config option for a diff driver, so that one can explicitly set diff.foo.binary. We default this value to "don't know". That is, setting a diff attribute to "foo" and using "diff.foo.funcname" will have no effect on the binaryness of a file. To get the current behavior, one can set diff.foo.binary to true. This patch also has one additional advantage: it cleans up the interface to the userdiff code a bit. Before, calling code had to know more about whether attributes were false, true, or unset to determine binaryness. Now that binaryness is a property of a driver, we can represent these situations just by passing back a driver struct. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-06 05:43:36 +08:00
spec->is_binary = -1;
return spec;
}
void free_filespec(struct diff_filespec *spec)
{
if (!--spec->count) {
diff_free_filespec_data(spec);
free(spec);
}
}
void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1,
unsigned short mode)
{
if (mode) {
spec->mode = canon_mode(mode);
hashcpy(spec->sha1, sha1);
spec->sha1_valid = !is_null_sha1(sha1);
}
}
/*
* Given a name and sha1 pair, if the index tells us the file in
* the work tree has that object contents, return true, so that
* prepare_temp_file() does not have to inflate and extract.
*/
Avoid accessing a slow working copy during diffcore operations. The Cygwin folks have done a fine job at creating a POSIX layer on Windows That Just Works(tm). However it comes with a penalty; accessing files in the working tree by way of stat/open/mmap can be slower for diffcore than inflating the data from a blob which is stored in a packfile. This performance problem is especially an issue in merge-recursive when dealing with nearly 7000 added files, as we are loading each file's content from the working directory to perform rename detection. I have literally seen (and sadly watched) paint dry in less time than it takes for merge-recursive to finish such a merge. On the other hand this very same merge runs very fast on Solaris. If Git is compiled with NO_FAST_WORKING_DIRECTORY set then we will avoid looking at the working directory when the blob in question is available within a packfile and the caller doesn't need the data unpacked into a temporary file. We don't use loose objects as they have the same open/mmap/close costs as the working directory file access, but have the additional CPU overhead of needing to inflate the content before use. So it is still faster to use the working tree file over the loose object. If the caller needs the file data unpacked into a temporary file its likely because they are going to call an external diff program, passing the file as a parameter. In this case reusing the working tree file will be faster as we don't need to inflate the data and write it out to a temporary file. The NO_FAST_WORKING_DIRECTORY feature is enabled by default on Cygwin, as that is the platform which currently appears to benefit the most from this option. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-12-14 19:15:57 +08:00
static int reuse_worktree_file(const char *name, const unsigned char *sha1, int want_file)
{
struct cache_entry *ce;
struct stat st;
int pos, len;
/*
* We do not read the cache ourselves here, because the
* benchmark with my previous version that always reads cache
* shows that it makes things worse for diff-tree comparing
* two linux-2.6 kernel trees in an already checked out work
* tree. This is because most diff-tree comparisons deal with
* only a small number of files, while reading the cache is
* expensive for a large project, and its cost outweighs the
* savings we get by not inflating the object to a temporary
* file. Practically, this code only helps when we are used
* by diff-cache --cached, which does read the cache before
* calling us.
*/
if (!active_cache)
return 0;
Avoid accessing a slow working copy during diffcore operations. The Cygwin folks have done a fine job at creating a POSIX layer on Windows That Just Works(tm). However it comes with a penalty; accessing files in the working tree by way of stat/open/mmap can be slower for diffcore than inflating the data from a blob which is stored in a packfile. This performance problem is especially an issue in merge-recursive when dealing with nearly 7000 added files, as we are loading each file's content from the working directory to perform rename detection. I have literally seen (and sadly watched) paint dry in less time than it takes for merge-recursive to finish such a merge. On the other hand this very same merge runs very fast on Solaris. If Git is compiled with NO_FAST_WORKING_DIRECTORY set then we will avoid looking at the working directory when the blob in question is available within a packfile and the caller doesn't need the data unpacked into a temporary file. We don't use loose objects as they have the same open/mmap/close costs as the working directory file access, but have the additional CPU overhead of needing to inflate the content before use. So it is still faster to use the working tree file over the loose object. If the caller needs the file data unpacked into a temporary file its likely because they are going to call an external diff program, passing the file as a parameter. In this case reusing the working tree file will be faster as we don't need to inflate the data and write it out to a temporary file. The NO_FAST_WORKING_DIRECTORY feature is enabled by default on Cygwin, as that is the platform which currently appears to benefit the most from this option. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-12-14 19:15:57 +08:00
/* We want to avoid the working directory if our caller
* doesn't need the data in a normal file, this system
* is rather slow with its stat/open/mmap/close syscalls,
* and the object is contained in a pack file. The pack
* is probably already open and will be faster to obtain
* the data through than the working directory. Loose
* objects however would tend to be slower as they need
* to be individually opened and inflated.
*/
if (!FAST_WORKING_DIRECTORY && !want_file && has_sha1_pack(sha1))
Avoid accessing a slow working copy during diffcore operations. The Cygwin folks have done a fine job at creating a POSIX layer on Windows That Just Works(tm). However it comes with a penalty; accessing files in the working tree by way of stat/open/mmap can be slower for diffcore than inflating the data from a blob which is stored in a packfile. This performance problem is especially an issue in merge-recursive when dealing with nearly 7000 added files, as we are loading each file's content from the working directory to perform rename detection. I have literally seen (and sadly watched) paint dry in less time than it takes for merge-recursive to finish such a merge. On the other hand this very same merge runs very fast on Solaris. If Git is compiled with NO_FAST_WORKING_DIRECTORY set then we will avoid looking at the working directory when the blob in question is available within a packfile and the caller doesn't need the data unpacked into a temporary file. We don't use loose objects as they have the same open/mmap/close costs as the working directory file access, but have the additional CPU overhead of needing to inflate the content before use. So it is still faster to use the working tree file over the loose object. If the caller needs the file data unpacked into a temporary file its likely because they are going to call an external diff program, passing the file as a parameter. In this case reusing the working tree file will be faster as we don't need to inflate the data and write it out to a temporary file. The NO_FAST_WORKING_DIRECTORY feature is enabled by default on Cygwin, as that is the platform which currently appears to benefit the most from this option. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-12-14 19:15:57 +08:00
return 0;
len = strlen(name);
pos = cache_name_pos(name, len);
if (pos < 0)
return 0;
ce = active_cache[pos];
/*
* This is not the sha1 we are looking for, or
* unreusable because it is not a regular file.
*/
if (hashcmp(sha1, ce->sha1) || !S_ISREG(ce->ce_mode))
return 0;
/*
* If ce is marked as "assume unchanged", there is no
* guarantee that work tree matches what we are looking for.
*/
if ((ce->ce_flags & CE_VALID) || ce_skip_worktree(ce))
return 0;
/*
* If ce matches the file in the work tree, we can reuse it.
*/
if (ce_uptodate(ce) ||
(!lstat(name, &st) && !ce_match_stat(ce, &st, 0)))
return 1;
return 0;
}
static int populate_from_stdin(struct diff_filespec *s)
{
struct strbuf buf = STRBUF_INIT;
size_t size = 0;
if (strbuf_read(&buf, 0, 0) < 0)
return error("error while reading from stdin %s",
strerror(errno));
s->should_munmap = 0;
s->data = strbuf_detach(&buf, &size);
s->size = size;
s->should_free = 1;
return 0;
}
static int diff_populate_gitlink(struct diff_filespec *s, int size_only)
{
int len;
char *data = xmalloc(100), *dirty = "";
/* Are we looking at the work tree? */
if (!s->sha1_valid && s->dirty_submodule)
dirty = "-dirty";
len = snprintf(data, 100,
"Subproject commit %s%s\n", sha1_to_hex(s->sha1), dirty);
s->data = data;
s->size = len;
s->should_free = 1;
if (size_only) {
s->data = NULL;
free(data);
}
return 0;
}
/*
* While doing rename detection and pickaxe operation, we may need to
* grab the data for the blob (or file) for our own in-core comparison.
* diff_filespec has data and size fields for this purpose.
*/
int diff_populate_filespec(struct diff_filespec *s, int size_only)
{
int err = 0;
if (!DIFF_FILE_VALID(s))
die("internal error: asking to populate invalid file.");
if (S_ISDIR(s->mode))
return -1;
if (s->data)
return 0;
if (size_only && 0 < s->size)
return 0;
if (S_ISGITLINK(s->mode))
return diff_populate_gitlink(s, size_only);
if (!s->sha1_valid ||
Avoid accessing a slow working copy during diffcore operations. The Cygwin folks have done a fine job at creating a POSIX layer on Windows That Just Works(tm). However it comes with a penalty; accessing files in the working tree by way of stat/open/mmap can be slower for diffcore than inflating the data from a blob which is stored in a packfile. This performance problem is especially an issue in merge-recursive when dealing with nearly 7000 added files, as we are loading each file's content from the working directory to perform rename detection. I have literally seen (and sadly watched) paint dry in less time than it takes for merge-recursive to finish such a merge. On the other hand this very same merge runs very fast on Solaris. If Git is compiled with NO_FAST_WORKING_DIRECTORY set then we will avoid looking at the working directory when the blob in question is available within a packfile and the caller doesn't need the data unpacked into a temporary file. We don't use loose objects as they have the same open/mmap/close costs as the working directory file access, but have the additional CPU overhead of needing to inflate the content before use. So it is still faster to use the working tree file over the loose object. If the caller needs the file data unpacked into a temporary file its likely because they are going to call an external diff program, passing the file as a parameter. In this case reusing the working tree file will be faster as we don't need to inflate the data and write it out to a temporary file. The NO_FAST_WORKING_DIRECTORY feature is enabled by default on Cygwin, as that is the platform which currently appears to benefit the most from this option. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-12-14 19:15:57 +08:00
reuse_worktree_file(s->path, s->sha1, 0)) {
struct strbuf buf = STRBUF_INIT;
struct stat st;
int fd;
Lazy man's auto-CRLF It currently does NOT know about file attributes, so it does its conversion purely based on content. Maybe that is more in the "git philosophy" anyway, since content is king, but I think we should try to do the file attributes to turn it off on demand. Anyway, BY DEFAULT it is off regardless, because it requires a [core] AutoCRLF = true in your config file to be enabled. We could make that the default for Windows, of course, the same way we do some other things (filemode etc). But you can actually enable it on UNIX, and it will cause: - "git update-index" will write blobs without CRLF - "git diff" will diff working tree files without CRLF - "git checkout" will write files to the working tree _with_ CRLF and things work fine. Funnily, it actually shows an odd file in git itself: git clone -n git test-crlf cd test-crlf git config core.autocrlf true git checkout git diff shows a diff for "Documentation/docbook-xsl.css". Why? Because we have actually checked in that file *with* CRLF! So when "core.autocrlf" is true, we'll always generate a *different* hash for it in the index, because the index hash will be for the content _without_ CRLF. Is this complete? I dunno. It seems to work for me. It doesn't use the filename at all right now, and that's probably a deficiency (we could certainly make the "is_binary()" heuristics also take standard filename heuristics into account). I don't pass in the filename at all for the "index_fd()" case (git-update-index), so that would need to be passed around, but this actually works fine. NOTE NOTE NOTE! The "is_binary()" heuristics are totally made-up by yours truly. I will not guarantee that they work at all reasonable. Caveat emptor. But it _is_ simple, and it _is_ safe, since it's all off by default. The patch is pretty simple - the biggest part is the new "convert.c" file, but even that is really just basic stuff that anybody can write in "Teaching C 101" as a final project for their first class in programming. Not to say that it's bug-free, of course - but at least we're not talking about rocket surgery here. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-02-14 03:07:23 +08:00
if (!strcmp(s->path, "-"))
return populate_from_stdin(s);
if (lstat(s->path, &st) < 0) {
if (errno == ENOENT) {
err_empty:
err = -1;
empty:
s->data = (char *)"";
s->size = 0;
return err;
}
}
s->size = xsize_t(st.st_size);
if (!s->size)
goto empty;
if (S_ISLNK(st.st_mode)) {
struct strbuf sb = STRBUF_INIT;
if (strbuf_readlink(&sb, s->path, s->size))
goto err_empty;
s->size = sb.len;
s->data = strbuf_detach(&sb, NULL);
s->should_free = 1;
return 0;
}
if (size_only)
return 0;
fd = open(s->path, O_RDONLY);
if (fd < 0)
goto err_empty;
s->data = xmmap(NULL, s->size, PROT_READ, MAP_PRIVATE, fd, 0);
close(fd);
s->should_munmap = 1;
Lazy man's auto-CRLF It currently does NOT know about file attributes, so it does its conversion purely based on content. Maybe that is more in the "git philosophy" anyway, since content is king, but I think we should try to do the file attributes to turn it off on demand. Anyway, BY DEFAULT it is off regardless, because it requires a [core] AutoCRLF = true in your config file to be enabled. We could make that the default for Windows, of course, the same way we do some other things (filemode etc). But you can actually enable it on UNIX, and it will cause: - "git update-index" will write blobs without CRLF - "git diff" will diff working tree files without CRLF - "git checkout" will write files to the working tree _with_ CRLF and things work fine. Funnily, it actually shows an odd file in git itself: git clone -n git test-crlf cd test-crlf git config core.autocrlf true git checkout git diff shows a diff for "Documentation/docbook-xsl.css". Why? Because we have actually checked in that file *with* CRLF! So when "core.autocrlf" is true, we'll always generate a *different* hash for it in the index, because the index hash will be for the content _without_ CRLF. Is this complete? I dunno. It seems to work for me. It doesn't use the filename at all right now, and that's probably a deficiency (we could certainly make the "is_binary()" heuristics also take standard filename heuristics into account). I don't pass in the filename at all for the "index_fd()" case (git-update-index), so that would need to be passed around, but this actually works fine. NOTE NOTE NOTE! The "is_binary()" heuristics are totally made-up by yours truly. I will not guarantee that they work at all reasonable. Caveat emptor. But it _is_ simple, and it _is_ safe, since it's all off by default. The patch is pretty simple - the biggest part is the new "convert.c" file, but even that is really just basic stuff that anybody can write in "Teaching C 101" as a final project for their first class in programming. Not to say that it's bug-free, of course - but at least we're not talking about rocket surgery here. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-02-14 03:07:23 +08:00
/*
* Convert from working tree format to canonical git format
*/
safecrlf: Add mechanism to warn about irreversible crlf conversions CRLF conversion bears a slight chance of corrupting data. autocrlf=true will convert CRLF to LF during commit and LF to CRLF during checkout. A file that contains a mixture of LF and CRLF before the commit cannot be recreated by git. For text files this is the right thing to do: it corrects line endings such that we have only LF line endings in the repository. But for binary files that are accidentally classified as text the conversion can corrupt data. If you recognize such corruption early you can easily fix it by setting the conversion type explicitly in .gitattributes. Right after committing you still have the original file in your work tree and this file is not yet corrupted. You can explicitly tell git that this file is binary and git will handle the file appropriately. Unfortunately, the desired effect of cleaning up text files with mixed line endings and the undesired effect of corrupting binary files cannot be distinguished. In both cases CRLFs are removed in an irreversible way. For text files this is the right thing to do because CRLFs are line endings, while for binary files converting CRLFs corrupts data. This patch adds a mechanism that can either warn the user about an irreversible conversion or can even refuse to convert. The mechanism is controlled by the variable core.safecrlf, with the following values: - false: disable safecrlf mechanism - warn: warn about irreversible conversions - true: refuse irreversible conversions The default is to warn. Users are only affected by this default if core.autocrlf is set. But the current default of git is to leave core.autocrlf unset, so users will not see warnings unless they deliberately chose to activate the autocrlf mechanism. The safecrlf mechanism's details depend on the git command. The general principles when safecrlf is active (not false) are: - we warn/error out if files in the work tree can modified in an irreversible way without giving the user a chance to backup the original file. - for read-only operations that do not modify files in the work tree we do not not print annoying warnings. There are exceptions. Even though... - "git add" itself does not touch the files in the work tree, the next checkout would, so the safety triggers; - "git apply" to update a text file with a patch does touch the files in the work tree, but the operation is about text files and CRLF conversion is about fixing the line ending inconsistencies, so the safety does not trigger; - "git diff" itself does not touch the files in the work tree, it is often run to inspect the changes you intend to next "git add". To catch potential problems early, safety triggers. The concept of a safety check was originally proposed in a similar way by Linus Torvalds. Thanks to Dimitry Potapov for insisting on getting the naked LF/autocrlf=true case right. Signed-off-by: Steffen Prohaska <prohaska@zib.de>
2008-02-06 19:25:58 +08:00
if (convert_to_git(s->path, s->data, s->size, &buf, safe_crlf)) {
size_t size = 0;
Lazy man's auto-CRLF It currently does NOT know about file attributes, so it does its conversion purely based on content. Maybe that is more in the "git philosophy" anyway, since content is king, but I think we should try to do the file attributes to turn it off on demand. Anyway, BY DEFAULT it is off regardless, because it requires a [core] AutoCRLF = true in your config file to be enabled. We could make that the default for Windows, of course, the same way we do some other things (filemode etc). But you can actually enable it on UNIX, and it will cause: - "git update-index" will write blobs without CRLF - "git diff" will diff working tree files without CRLF - "git checkout" will write files to the working tree _with_ CRLF and things work fine. Funnily, it actually shows an odd file in git itself: git clone -n git test-crlf cd test-crlf git config core.autocrlf true git checkout git diff shows a diff for "Documentation/docbook-xsl.css". Why? Because we have actually checked in that file *with* CRLF! So when "core.autocrlf" is true, we'll always generate a *different* hash for it in the index, because the index hash will be for the content _without_ CRLF. Is this complete? I dunno. It seems to work for me. It doesn't use the filename at all right now, and that's probably a deficiency (we could certainly make the "is_binary()" heuristics also take standard filename heuristics into account). I don't pass in the filename at all for the "index_fd()" case (git-update-index), so that would need to be passed around, but this actually works fine. NOTE NOTE NOTE! The "is_binary()" heuristics are totally made-up by yours truly. I will not guarantee that they work at all reasonable. Caveat emptor. But it _is_ simple, and it _is_ safe, since it's all off by default. The patch is pretty simple - the biggest part is the new "convert.c" file, but even that is really just basic stuff that anybody can write in "Teaching C 101" as a final project for their first class in programming. Not to say that it's bug-free, of course - but at least we're not talking about rocket surgery here. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-02-14 03:07:23 +08:00
munmap(s->data, s->size);
s->should_munmap = 0;
s->data = strbuf_detach(&buf, &size);
s->size = size;
Lazy man's auto-CRLF It currently does NOT know about file attributes, so it does its conversion purely based on content. Maybe that is more in the "git philosophy" anyway, since content is king, but I think we should try to do the file attributes to turn it off on demand. Anyway, BY DEFAULT it is off regardless, because it requires a [core] AutoCRLF = true in your config file to be enabled. We could make that the default for Windows, of course, the same way we do some other things (filemode etc). But you can actually enable it on UNIX, and it will cause: - "git update-index" will write blobs without CRLF - "git diff" will diff working tree files without CRLF - "git checkout" will write files to the working tree _with_ CRLF and things work fine. Funnily, it actually shows an odd file in git itself: git clone -n git test-crlf cd test-crlf git config core.autocrlf true git checkout git diff shows a diff for "Documentation/docbook-xsl.css". Why? Because we have actually checked in that file *with* CRLF! So when "core.autocrlf" is true, we'll always generate a *different* hash for it in the index, because the index hash will be for the content _without_ CRLF. Is this complete? I dunno. It seems to work for me. It doesn't use the filename at all right now, and that's probably a deficiency (we could certainly make the "is_binary()" heuristics also take standard filename heuristics into account). I don't pass in the filename at all for the "index_fd()" case (git-update-index), so that would need to be passed around, but this actually works fine. NOTE NOTE NOTE! The "is_binary()" heuristics are totally made-up by yours truly. I will not guarantee that they work at all reasonable. Caveat emptor. But it _is_ simple, and it _is_ safe, since it's all off by default. The patch is pretty simple - the biggest part is the new "convert.c" file, but even that is really just basic stuff that anybody can write in "Teaching C 101" as a final project for their first class in programming. Not to say that it's bug-free, of course - but at least we're not talking about rocket surgery here. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-02-14 03:07:23 +08:00
s->should_free = 1;
}
}
else {
enum object_type type;
if (size_only)
type = sha1_object_info(s->sha1, &s->size);
else {
s->data = read_sha1_file(s->sha1, &type, &s->size);
s->should_free = 1;
}
}
return 0;
}
void diff_free_filespec_blob(struct diff_filespec *s)
{
if (s->should_free)
free(s->data);
else if (s->should_munmap)
munmap(s->data, s->size);
if (s->should_free || s->should_munmap) {
s->should_free = s->should_munmap = 0;
s->data = NULL;
}
}
void diff_free_filespec_data(struct diff_filespec *s)
{
diff_free_filespec_blob(s);
free(s->cnt_data);
s->cnt_data = NULL;
}
static void prep_temp_blob(const char *path, struct diff_tempfile *temp,
void *blob,
unsigned long size,
const unsigned char *sha1,
int mode)
{
int fd;
struct strbuf buf = STRBUF_INIT;
struct strbuf template = STRBUF_INIT;
char *path_dup = xstrdup(path);
const char *base = basename(path_dup);
/* Generate "XXXXXX_basename.ext" */
strbuf_addstr(&template, "XXXXXX_");
strbuf_addstr(&template, base);
fd = git_mkstemps(temp->tmp_path, PATH_MAX, template.buf,
strlen(base) + 1);
if (fd < 0)
die_errno("unable to create temp-file");
if (convert_to_working_tree(path,
(const char *)blob, (size_t)size, &buf)) {
blob = buf.buf;
size = buf.len;
}
if (write_in_full(fd, blob, size) != size)
die_errno("unable to write temp-file");
close(fd);
temp->name = temp->tmp_path;
strcpy(temp->hex, sha1_to_hex(sha1));
temp->hex[40] = 0;
sprintf(temp->mode, "%06o", mode);
strbuf_release(&buf);
strbuf_release(&template);
free(path_dup);
}
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
static struct diff_tempfile *prepare_temp_file(const char *name,
struct diff_filespec *one)
{
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
struct diff_tempfile *temp = claim_diff_tempfile();
if (!DIFF_FILE_VALID(one)) {
not_a_valid_file:
/* A '-' entry produces this for file-2, and
* a '+' entry produces this for file-1.
*/
temp->name = "/dev/null";
strcpy(temp->hex, ".");
strcpy(temp->mode, ".");
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
return temp;
}
if (!remove_tempfile_installed) {
atexit(remove_tempfile);
sigchain_push_common(remove_tempfile_on_signal);
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
remove_tempfile_installed = 1;
}
if (!one->sha1_valid ||
Avoid accessing a slow working copy during diffcore operations. The Cygwin folks have done a fine job at creating a POSIX layer on Windows That Just Works(tm). However it comes with a penalty; accessing files in the working tree by way of stat/open/mmap can be slower for diffcore than inflating the data from a blob which is stored in a packfile. This performance problem is especially an issue in merge-recursive when dealing with nearly 7000 added files, as we are loading each file's content from the working directory to perform rename detection. I have literally seen (and sadly watched) paint dry in less time than it takes for merge-recursive to finish such a merge. On the other hand this very same merge runs very fast on Solaris. If Git is compiled with NO_FAST_WORKING_DIRECTORY set then we will avoid looking at the working directory when the blob in question is available within a packfile and the caller doesn't need the data unpacked into a temporary file. We don't use loose objects as they have the same open/mmap/close costs as the working directory file access, but have the additional CPU overhead of needing to inflate the content before use. So it is still faster to use the working tree file over the loose object. If the caller needs the file data unpacked into a temporary file its likely because they are going to call an external diff program, passing the file as a parameter. In this case reusing the working tree file will be faster as we don't need to inflate the data and write it out to a temporary file. The NO_FAST_WORKING_DIRECTORY feature is enabled by default on Cygwin, as that is the platform which currently appears to benefit the most from this option. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-12-14 19:15:57 +08:00
reuse_worktree_file(name, one->sha1, 1)) {
struct stat st;
if (lstat(name, &st) < 0) {
if (errno == ENOENT)
goto not_a_valid_file;
die_errno("stat(%s)", name);
}
if (S_ISLNK(st.st_mode)) {
struct strbuf sb = STRBUF_INIT;
if (strbuf_readlink(&sb, name, st.st_size) < 0)
die_errno("readlink(%s)", name);
prep_temp_blob(name, temp, sb.buf, sb.len,
(one->sha1_valid ?
one->sha1 : null_sha1),
(one->sha1_valid ?
one->mode : S_IFLNK));
strbuf_release(&sb);
}
else {
/* we can borrow from the file in the work tree */
temp->name = name;
if (!one->sha1_valid)
strcpy(temp->hex, sha1_to_hex(null_sha1));
else
strcpy(temp->hex, sha1_to_hex(one->sha1));
/* Even though we may sometimes borrow the
* contents from the work tree, we always want
* one->mode. mode is trustworthy even when
* !(one->sha1_valid), as long as
* DIFF_FILE_VALID(one).
*/
sprintf(temp->mode, "%06o", one->mode);
}
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
return temp;
}
else {
if (diff_populate_filespec(one, 0))
die("cannot read data blob for %s", one->path);
prep_temp_blob(name, temp, one->data, one->size,
one->sha1, one->mode);
}
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
return temp;
}
/* An external diff command takes:
*
* diff-cmd name infile1 infile1-sha1 infile1-mode \
* infile2 infile2-sha1 infile2-mode [ rename-to ]
*
*/
static void run_external_diff(const char *pgm,
const char *name,
const char *other,
struct diff_filespec *one,
struct diff_filespec *two,
const char *xfrm_msg,
int complete_rewrite)
{
const char *spawn_arg[10];
int retval;
const char **arg = &spawn_arg[0];
if (one && two) {
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
struct diff_tempfile *temp_one, *temp_two;
const char *othername = (other ? other : name);
temp_one = prepare_temp_file(name, one);
temp_two = prepare_temp_file(othername, two);
*arg++ = pgm;
*arg++ = name;
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
*arg++ = temp_one->name;
*arg++ = temp_one->hex;
*arg++ = temp_one->mode;
*arg++ = temp_two->name;
*arg++ = temp_two->hex;
*arg++ = temp_two->mode;
if (other) {
*arg++ = other;
*arg++ = xfrm_msg;
}
} else {
*arg++ = pgm;
*arg++ = name;
}
*arg = NULL;
fflush(NULL);
retval = run_command_v_opt(spawn_arg, RUN_USING_SHELL);
remove_tempfile();
if (retval) {
fprintf(stderr, "external diff died, stopping at %s.\n", name);
exit(1);
}
}
static int similarity_index(struct diff_filepair *p)
{
return p->score * 100 / MAX_SCORE;
}
static void fill_metainfo(struct strbuf *msg,
const char *name,
const char *other,
struct diff_filespec *one,
struct diff_filespec *two,
struct diff_options *o,
struct diff_filepair *p)
{
strbuf_init(msg, PATH_MAX * 2 + 300);
switch (p->status) {
case DIFF_STATUS_COPIED:
strbuf_addf(msg, "similarity index %d%%", similarity_index(p));
strbuf_addstr(msg, "\ncopy from ");
quote_c_style(name, msg, NULL, 0);
strbuf_addstr(msg, "\ncopy to ");
quote_c_style(other, msg, NULL, 0);
strbuf_addch(msg, '\n');
break;
case DIFF_STATUS_RENAMED:
strbuf_addf(msg, "similarity index %d%%", similarity_index(p));
strbuf_addstr(msg, "\nrename from ");
quote_c_style(name, msg, NULL, 0);
strbuf_addstr(msg, "\nrename to ");
quote_c_style(other, msg, NULL, 0);
strbuf_addch(msg, '\n');
break;
case DIFF_STATUS_MODIFIED:
if (p->score) {
strbuf_addf(msg, "dissimilarity index %d%%\n",
similarity_index(p));
break;
}
/* fallthru */
default:
/* nothing */
;
}
if (one && two && hashcmp(one->sha1, two->sha1)) {
int abbrev = DIFF_OPT_TST(o, FULL_INDEX) ? 40 : DEFAULT_ABBREV;
if (DIFF_OPT_TST(o, BINARY)) {
mmfile_t mf;
if ((!fill_mmfile(&mf, one) && diff_filespec_is_binary(one)) ||
(!fill_mmfile(&mf, two) && diff_filespec_is_binary(two)))
abbrev = 40;
}
strbuf_addf(msg, "index %.*s..%.*s",
abbrev, sha1_to_hex(one->sha1),
abbrev, sha1_to_hex(two->sha1));
if (one->mode == two->mode)
strbuf_addf(msg, " %06o", one->mode);
strbuf_addch(msg, '\n');
}
if (msg->len)
strbuf_setlen(msg, msg->len - 1);
}
static void run_diff_cmd(const char *pgm,
const char *name,
const char *other,
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
const char *attr_path,
struct diff_filespec *one,
struct diff_filespec *two,
struct strbuf *msg,
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
struct diff_options *o,
struct diff_filepair *p)
{
const char *xfrm_msg = NULL;
int complete_rewrite = (p->status == DIFF_STATUS_MODIFIED) && p->score;
if (msg) {
fill_metainfo(msg, name, other, one, two, o, p);
xfrm_msg = msg->len ? msg->buf : NULL;
}
if (!DIFF_OPT_TST(o, ALLOW_EXTERNAL))
pgm = NULL;
else {
struct userdiff_driver *drv = userdiff_find_by_path(attr_path);
if (drv && drv->external)
pgm = drv->external;
}
if (pgm) {
run_external_diff(pgm, name, other, one, two, xfrm_msg,
complete_rewrite);
return;
}
if (one && two)
builtin_diff(name, other ? other : name,
binary patch. This adds "binary patch" to the diff output and teaches apply what to do with them. On the diff generation side, traditionally, we said "Binary files differ\n" without giving anything other than the preimage and postimage object name on the index line. This was good enough for applying a patch generated from your own repository (very useful while rebasing), because the postimage would be available in such a case. However, this was not useful when the recipient of such a patch via e-mail were to apply it, even if the preimage was available. This patch allows the diff to generate "binary" patch when operating under --full-index option. The binary patch follows the usual extended git diff headers, and looks like this: "GIT binary patch\n" <length byte><data>"\n" ... "\n" Each line is prefixed with a "length-byte", whose value is upper or lowercase alphabet that encodes number of bytes that the data on the line decodes to (1..52 -- 'A' means 1, 'B' means 2, ..., 'Z' means 26, 'a' means 27, ...). <data> is 1 or more groups of 5-byte sequence, each of which encodes up to 4 bytes in base85 encoding. Because 52 / 4 * 5 = 65 and we have the length byte, an output line is capped to 66 characters. The payload is the same diff-delta as we use in the packfiles. On the consumption side, git-apply now can decode and apply the binary patch when --allow-binary-replacement is given, the diff was generated with --full-index, and the receiving repository has the preimage blob, which is the same condition as it always required when accepting an "Binary files differ\n" patch. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-05 07:51:44 +08:00
one, two, xfrm_msg, o, complete_rewrite);
else
fprintf(o->file, "* Unmerged path %s\n", name);
}
static void diff_fill_sha1_info(struct diff_filespec *one)
{
if (DIFF_FILE_VALID(one)) {
if (!one->sha1_valid) {
struct stat st;
if (!strcmp(one->path, "-")) {
hashcpy(one->sha1, null_sha1);
return;
}
if (lstat(one->path, &st) < 0)
die_errno("stat '%s'", one->path);
if (index_path(one->sha1, one->path, &st, 0))
die("cannot hash %s", one->path);
}
}
else
hashclr(one->sha1);
}
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
static void strip_prefix(int prefix_length, const char **namep, const char **otherp)
{
/* Strip the prefix but do not molest /dev/null and absolute paths */
if (*namep && **namep != '/')
*namep += prefix_length;
if (*otherp && **otherp != '/')
*otherp += prefix_length;
}
static void run_diff(struct diff_filepair *p, struct diff_options *o)
{
const char *pgm = external_diff();
struct strbuf msg;
struct diff_filespec *one = p->one;
struct diff_filespec *two = p->two;
const char *name;
const char *other;
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
const char *attr_path;
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
name = p->one->path;
other = (strcmp(name, p->two->path) ? p->two->path : NULL);
attr_path = name;
if (o->prefix_length)
strip_prefix(o->prefix_length, &name, &other);
if (DIFF_PAIR_UNMERGED(p)) {
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
run_diff_cmd(pgm, name, NULL, attr_path,
NULL, NULL, NULL, o, p);
return;
}
diff_fill_sha1_info(one);
diff_fill_sha1_info(two);
if (!pgm &&
DIFF_FILE_VALID(one) && DIFF_FILE_VALID(two) &&
(S_IFMT & one->mode) != (S_IFMT & two->mode)) {
/*
* a filepair that changes between file and symlink
* needs to be split into deletion and creation.
*/
struct diff_filespec *null = alloc_filespec(two->path);
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
run_diff_cmd(NULL, name, other, attr_path,
one, null, &msg, o, p);
free(null);
strbuf_release(&msg);
null = alloc_filespec(one->path);
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
run_diff_cmd(NULL, name, other, attr_path,
null, two, &msg, o, p);
free(null);
}
else
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
run_diff_cmd(pgm, name, other, attr_path,
one, two, &msg, o, p);
strbuf_release(&msg);
}
static void run_diffstat(struct diff_filepair *p, struct diff_options *o,
struct diffstat_t *diffstat)
{
const char *name;
const char *other;
int complete_rewrite = 0;
if (DIFF_PAIR_UNMERGED(p)) {
/* unmerged */
builtin_diffstat(p->one->path, NULL, NULL, NULL, diffstat, o, 0);
return;
}
name = p->one->path;
other = (strcmp(name, p->two->path) ? p->two->path : NULL);
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
if (o->prefix_length)
strip_prefix(o->prefix_length, &name, &other);
diff_fill_sha1_info(p->one);
diff_fill_sha1_info(p->two);
if (p->status == DIFF_STATUS_MODIFIED && p->score)
complete_rewrite = 1;
builtin_diffstat(name, other, p->one, p->two, diffstat, o, complete_rewrite);
}
static void run_checkdiff(struct diff_filepair *p, struct diff_options *o)
{
const char *name;
const char *other;
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
const char *attr_path;
if (DIFF_PAIR_UNMERGED(p)) {
/* unmerged */
return;
}
name = p->one->path;
other = (strcmp(name, p->two->path) ? p->two->path : NULL);
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
attr_path = other ? other : name;
if (o->prefix_length)
strip_prefix(o->prefix_length, &name, &other);
diff_fill_sha1_info(p->one);
diff_fill_sha1_info(p->two);
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
builtin_checkdiff(name, other, attr_path, p->one, p->two, o);
}
void diff_setup(struct diff_options *options)
{
memset(options, 0, sizeof(*options));
options->file = stdout;
options->line_termination = '\n';
options->break_opt = -1;
options->rename_limit = -1;
Add "--dirstat" for some directory statistics This adds a new form of overview diffstat output, doing something that I have occasionally ended up doing manually (and badly, because it's actually pretty nasty to do), and that I think is very useful for an project like the kernel that has a fairly deep and well-separated directory structure with semantic meaning. What I mean by that is that it's often interesting to see exactly which sub-directories are impacted by a patch, and to what degree - even if you don't perhaps care so much about the individual files themselves. What makes the concept more interesting is that the "impact" is often hierarchical: in the kernel, for example, something could either have a very localized impact to "fs/ext3/" and then it's interesting to see that such a patch changes mostly that subdirectory, but you could have another patch that changes some generic VFS-layer issue which affects _many_ subdirectories that are all under "fs/", but none - or perhaps just a couple of them - of the individual filesystems are interesting in themselves. So what commonly happens is that you may have big changes in a specific sub-subdirectory, but still also significant separate changes to the subdirectory leading up to that - maybe you have significant VFS-level changes, but *also* changes under that VFS layer in the NFS-specific directories, for example. In that case, you do want the low-level parts that are significant to show up, but then the insignificant ones should show up as under the more generic top-level directory. This patch shows all of that with "--dirstat". The output can be either something simple like commit 81772fe... Author: Thomas Gleixner <tglx@linutronix.de> Date: Sun Feb 10 23:57:36 2008 +0100 x86: remove over noisy debug printk pageattr-test.c contains a noisy debug printk that people reported. The condition under which it prints (randomly tapping into a mem_map[] hole and not being able to c_p_a() there) is valid behavior and not interesting to report. Remove it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 100.0% arch/x86/mm/ or something much more complex like commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 15.3% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ where that latter example is an example of significant work in some individual fs/*/ subdirectories (like the patches to reiserfs accounting for 7.6% of the whole), but then discounting those individual filesystems, there's also 15.3% other "random" things that weren't worth reporting on their oen left over under fs/ in general (either in that directory itself, or in subdirectories of fs/ that didn't have enough changes to be reported individually). I'd like to stress that the "15.3% fs/" mentioned above is the stuff that is under fs/ but that was _not_ significant enough to report on its own. So the above does _not_ mean that 15.3% of the work was under fs/ per se, because that 15.3% does *not* include the already-reported 7.6% of afs, 7.6% of fuse etc. If you want to enable "cumulative" directory statistics, you can use the "--cumulative" flag, which adds up percentages recursively even when they have been already reported for a sub-directory. That cumulative output is disabled if *all* of the changes in one subdirectory come from a deeper subdirectory, to avoid repeating subdirectories all the way to the root. For an example of the cumulative reporting, the above commit becomes commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 61.5% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ in which the commit percentages now obviously add up to much more than 100%: now the changes that were already reported for the sub-directories under fs/ are then cumulatively included in the whole percentage of fs/ (ie now shows 61.5% as opposed to the 15.3% without the cumulative reporting). The default reporting limit has been arbitrarily set at 3%, which seems to be a pretty good cut-off, but you can specify the cut-off manually by giving it as an option parameter (eg "--dirstat=5" makes the cut-off be at 5% instead) NOTE! The percentages are purely about the total lines added and removed, not anything smarter (or dumber) than that. Also note that you should not generally expect things to add up to 100%: not only does it round down, we don't report leftover scraps (they add up to the top-level change count, but we don't even bother reporting that, it only reports subdirectories). Quite frankly, as a top-level manager this is really convenient for me, but it's going to be very boring for git itself since there are few subdirectories. Also, don't expect things to make tons of sense if you combine this with "-M" and there are cross-directory renames etc. But even for git itself, you can get some fun statistics. Try out git log --dirstat and see the occasional mentions of things like Documentation/, git-gui/, gitweb/ and gitk-git/. Or try out something like git diff --dirstat v1.5.0..v1.5.4 which does kind of git an overview that shows *something*. But in general, the output is more exciting for big projects with deeper structure, and doing a git diff --dirstat v2.6.24..v2.6.25-rc1 on the kernel is what I actually wrote this for! Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 05:26:31 +08:00
options->dirstat_percent = 3;
options->context = 3;
options->change = diff_change;
options->add_remove = diff_addremove;
if (diff_use_color_default > 0)
DIFF_OPT_SET(options, COLOR_DIFF);
options->detect_rename = diff_detect_rename_default;
if (!diff_mnemonic_prefix) {
options->a_prefix = "a/";
options->b_prefix = "b/";
}
}
int diff_setup_done(struct diff_options *options)
{
int count = 0;
if (options->output_format & DIFF_FORMAT_NAME)
count++;
if (options->output_format & DIFF_FORMAT_NAME_STATUS)
count++;
if (options->output_format & DIFF_FORMAT_CHECKDIFF)
count++;
if (options->output_format & DIFF_FORMAT_NO_OUTPUT)
count++;
if (count > 1)
die("--name-only, --name-status, --check and -s are mutually exclusive");
/*
* Most of the time we can say "there are changes"
* only by checking if there are changed paths, but
* --ignore-whitespace* options force us to look
* inside contents.
*/
if (DIFF_XDL_TST(options, IGNORE_WHITESPACE) ||
DIFF_XDL_TST(options, IGNORE_WHITESPACE_CHANGE) ||
DIFF_XDL_TST(options, IGNORE_WHITESPACE_AT_EOL))
DIFF_OPT_SET(options, DIFF_FROM_CONTENTS);
else
DIFF_OPT_CLR(options, DIFF_FROM_CONTENTS);
if (DIFF_OPT_TST(options, FIND_COPIES_HARDER))
options->detect_rename = DIFF_DETECT_COPY;
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
if (!DIFF_OPT_TST(options, RELATIVE_NAME))
options->prefix = NULL;
if (options->prefix)
options->prefix_length = strlen(options->prefix);
else
options->prefix_length = 0;
if (options->output_format & (DIFF_FORMAT_NAME |
DIFF_FORMAT_NAME_STATUS |
DIFF_FORMAT_CHECKDIFF |
DIFF_FORMAT_NO_OUTPUT))
options->output_format &= ~(DIFF_FORMAT_RAW |
DIFF_FORMAT_NUMSTAT |
DIFF_FORMAT_DIFFSTAT |
DIFF_FORMAT_SHORTSTAT |
Add "--dirstat" for some directory statistics This adds a new form of overview diffstat output, doing something that I have occasionally ended up doing manually (and badly, because it's actually pretty nasty to do), and that I think is very useful for an project like the kernel that has a fairly deep and well-separated directory structure with semantic meaning. What I mean by that is that it's often interesting to see exactly which sub-directories are impacted by a patch, and to what degree - even if you don't perhaps care so much about the individual files themselves. What makes the concept more interesting is that the "impact" is often hierarchical: in the kernel, for example, something could either have a very localized impact to "fs/ext3/" and then it's interesting to see that such a patch changes mostly that subdirectory, but you could have another patch that changes some generic VFS-layer issue which affects _many_ subdirectories that are all under "fs/", but none - or perhaps just a couple of them - of the individual filesystems are interesting in themselves. So what commonly happens is that you may have big changes in a specific sub-subdirectory, but still also significant separate changes to the subdirectory leading up to that - maybe you have significant VFS-level changes, but *also* changes under that VFS layer in the NFS-specific directories, for example. In that case, you do want the low-level parts that are significant to show up, but then the insignificant ones should show up as under the more generic top-level directory. This patch shows all of that with "--dirstat". The output can be either something simple like commit 81772fe... Author: Thomas Gleixner <tglx@linutronix.de> Date: Sun Feb 10 23:57:36 2008 +0100 x86: remove over noisy debug printk pageattr-test.c contains a noisy debug printk that people reported. The condition under which it prints (randomly tapping into a mem_map[] hole and not being able to c_p_a() there) is valid behavior and not interesting to report. Remove it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 100.0% arch/x86/mm/ or something much more complex like commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 15.3% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ where that latter example is an example of significant work in some individual fs/*/ subdirectories (like the patches to reiserfs accounting for 7.6% of the whole), but then discounting those individual filesystems, there's also 15.3% other "random" things that weren't worth reporting on their oen left over under fs/ in general (either in that directory itself, or in subdirectories of fs/ that didn't have enough changes to be reported individually). I'd like to stress that the "15.3% fs/" mentioned above is the stuff that is under fs/ but that was _not_ significant enough to report on its own. So the above does _not_ mean that 15.3% of the work was under fs/ per se, because that 15.3% does *not* include the already-reported 7.6% of afs, 7.6% of fuse etc. If you want to enable "cumulative" directory statistics, you can use the "--cumulative" flag, which adds up percentages recursively even when they have been already reported for a sub-directory. That cumulative output is disabled if *all* of the changes in one subdirectory come from a deeper subdirectory, to avoid repeating subdirectories all the way to the root. For an example of the cumulative reporting, the above commit becomes commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 61.5% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ in which the commit percentages now obviously add up to much more than 100%: now the changes that were already reported for the sub-directories under fs/ are then cumulatively included in the whole percentage of fs/ (ie now shows 61.5% as opposed to the 15.3% without the cumulative reporting). The default reporting limit has been arbitrarily set at 3%, which seems to be a pretty good cut-off, but you can specify the cut-off manually by giving it as an option parameter (eg "--dirstat=5" makes the cut-off be at 5% instead) NOTE! The percentages are purely about the total lines added and removed, not anything smarter (or dumber) than that. Also note that you should not generally expect things to add up to 100%: not only does it round down, we don't report leftover scraps (they add up to the top-level change count, but we don't even bother reporting that, it only reports subdirectories). Quite frankly, as a top-level manager this is really convenient for me, but it's going to be very boring for git itself since there are few subdirectories. Also, don't expect things to make tons of sense if you combine this with "-M" and there are cross-directory renames etc. But even for git itself, you can get some fun statistics. Try out git log --dirstat and see the occasional mentions of things like Documentation/, git-gui/, gitweb/ and gitk-git/. Or try out something like git diff --dirstat v1.5.0..v1.5.4 which does kind of git an overview that shows *something*. But in general, the output is more exciting for big projects with deeper structure, and doing a git diff --dirstat v2.6.24..v2.6.25-rc1 on the kernel is what I actually wrote this for! Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 05:26:31 +08:00
DIFF_FORMAT_DIRSTAT |
DIFF_FORMAT_SUMMARY |
DIFF_FORMAT_PATCH);
/*
* These cases always need recursive; we do not drop caller-supplied
* recursive bits for other formats here.
*/
if (options->output_format & (DIFF_FORMAT_PATCH |
DIFF_FORMAT_NUMSTAT |
DIFF_FORMAT_DIFFSTAT |
DIFF_FORMAT_SHORTSTAT |
Add "--dirstat" for some directory statistics This adds a new form of overview diffstat output, doing something that I have occasionally ended up doing manually (and badly, because it's actually pretty nasty to do), and that I think is very useful for an project like the kernel that has a fairly deep and well-separated directory structure with semantic meaning. What I mean by that is that it's often interesting to see exactly which sub-directories are impacted by a patch, and to what degree - even if you don't perhaps care so much about the individual files themselves. What makes the concept more interesting is that the "impact" is often hierarchical: in the kernel, for example, something could either have a very localized impact to "fs/ext3/" and then it's interesting to see that such a patch changes mostly that subdirectory, but you could have another patch that changes some generic VFS-layer issue which affects _many_ subdirectories that are all under "fs/", but none - or perhaps just a couple of them - of the individual filesystems are interesting in themselves. So what commonly happens is that you may have big changes in a specific sub-subdirectory, but still also significant separate changes to the subdirectory leading up to that - maybe you have significant VFS-level changes, but *also* changes under that VFS layer in the NFS-specific directories, for example. In that case, you do want the low-level parts that are significant to show up, but then the insignificant ones should show up as under the more generic top-level directory. This patch shows all of that with "--dirstat". The output can be either something simple like commit 81772fe... Author: Thomas Gleixner <tglx@linutronix.de> Date: Sun Feb 10 23:57:36 2008 +0100 x86: remove over noisy debug printk pageattr-test.c contains a noisy debug printk that people reported. The condition under which it prints (randomly tapping into a mem_map[] hole and not being able to c_p_a() there) is valid behavior and not interesting to report. Remove it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 100.0% arch/x86/mm/ or something much more complex like commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 15.3% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ where that latter example is an example of significant work in some individual fs/*/ subdirectories (like the patches to reiserfs accounting for 7.6% of the whole), but then discounting those individual filesystems, there's also 15.3% other "random" things that weren't worth reporting on their oen left over under fs/ in general (either in that directory itself, or in subdirectories of fs/ that didn't have enough changes to be reported individually). I'd like to stress that the "15.3% fs/" mentioned above is the stuff that is under fs/ but that was _not_ significant enough to report on its own. So the above does _not_ mean that 15.3% of the work was under fs/ per se, because that 15.3% does *not* include the already-reported 7.6% of afs, 7.6% of fuse etc. If you want to enable "cumulative" directory statistics, you can use the "--cumulative" flag, which adds up percentages recursively even when they have been already reported for a sub-directory. That cumulative output is disabled if *all* of the changes in one subdirectory come from a deeper subdirectory, to avoid repeating subdirectories all the way to the root. For an example of the cumulative reporting, the above commit becomes commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 61.5% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ in which the commit percentages now obviously add up to much more than 100%: now the changes that were already reported for the sub-directories under fs/ are then cumulatively included in the whole percentage of fs/ (ie now shows 61.5% as opposed to the 15.3% without the cumulative reporting). The default reporting limit has been arbitrarily set at 3%, which seems to be a pretty good cut-off, but you can specify the cut-off manually by giving it as an option parameter (eg "--dirstat=5" makes the cut-off be at 5% instead) NOTE! The percentages are purely about the total lines added and removed, not anything smarter (or dumber) than that. Also note that you should not generally expect things to add up to 100%: not only does it round down, we don't report leftover scraps (they add up to the top-level change count, but we don't even bother reporting that, it only reports subdirectories). Quite frankly, as a top-level manager this is really convenient for me, but it's going to be very boring for git itself since there are few subdirectories. Also, don't expect things to make tons of sense if you combine this with "-M" and there are cross-directory renames etc. But even for git itself, you can get some fun statistics. Try out git log --dirstat and see the occasional mentions of things like Documentation/, git-gui/, gitweb/ and gitk-git/. Or try out something like git diff --dirstat v1.5.0..v1.5.4 which does kind of git an overview that shows *something*. But in general, the output is more exciting for big projects with deeper structure, and doing a git diff --dirstat v2.6.24..v2.6.25-rc1 on the kernel is what I actually wrote this for! Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 05:26:31 +08:00
DIFF_FORMAT_DIRSTAT |
DIFF_FORMAT_SUMMARY |
DIFF_FORMAT_CHECKDIFF))
DIFF_OPT_SET(options, RECURSIVE);
/*
* Also pickaxe would not work very well if you do not say recursive
*/
if (options->pickaxe)
DIFF_OPT_SET(options, RECURSIVE);
if (options->detect_rename && options->rename_limit < 0)
options->rename_limit = diff_rename_limit_default;
if (options->setup & DIFF_SETUP_USE_CACHE) {
if (!active_cache)
/* read-cache does not die even when it fails
* so it is safe for us to do this here. Also
* it does not smudge active_cache or active_nr
* when it fails, so we do not have to worry about
* cleaning it up ourselves either.
*/
read_cache();
}
if (options->abbrev <= 0 || 40 < options->abbrev)
options->abbrev = 40; /* full */
/*
* It does not make sense to show the first hit we happened
* to have found. It does not make sense not to return with
* exit code in such a case either.
*/
if (DIFF_OPT_TST(options, QUICK)) {
options->output_format = DIFF_FORMAT_NO_OUTPUT;
DIFF_OPT_SET(options, EXIT_WITH_STATUS);
}
return 0;
}
static int opt_arg(const char *arg, int arg_short, const char *arg_long, int *val)
{
char c, *eq;
int len;
if (*arg != '-')
return 0;
c = *++arg;
if (!c)
return 0;
if (c == arg_short) {
c = *++arg;
if (!c)
return 1;
if (val && isdigit(c)) {
char *end;
int n = strtoul(arg, &end, 10);
if (*end)
return 0;
*val = n;
return 1;
}
return 0;
}
if (c != '-')
return 0;
arg++;
eq = strchr(arg, '=');
if (eq)
len = eq - arg;
else
len = strlen(arg);
if (!len || strncmp(arg, arg_long, len))
return 0;
if (eq) {
int n;
char *end;
if (!isdigit(*++eq))
return 0;
n = strtoul(eq, &end, 10);
if (*end)
return 0;
*val = n;
}
return 1;
}
static int diff_scoreopt_parse(const char *opt);
int diff_opt_parse(struct diff_options *options, const char **av, int ac)
{
const char *arg = av[0];
/* Output format options */
if (!strcmp(arg, "-p") || !strcmp(arg, "-u"))
options->output_format |= DIFF_FORMAT_PATCH;
else if (opt_arg(arg, 'U', "unified", &options->context))
options->output_format |= DIFF_FORMAT_PATCH;
else if (!strcmp(arg, "--raw"))
options->output_format |= DIFF_FORMAT_RAW;
else if (!strcmp(arg, "--patch-with-raw"))
options->output_format |= DIFF_FORMAT_PATCH | DIFF_FORMAT_RAW;
else if (!strcmp(arg, "--numstat"))
options->output_format |= DIFF_FORMAT_NUMSTAT;
else if (!strcmp(arg, "--shortstat"))
options->output_format |= DIFF_FORMAT_SHORTSTAT;
Add "--dirstat" for some directory statistics This adds a new form of overview diffstat output, doing something that I have occasionally ended up doing manually (and badly, because it's actually pretty nasty to do), and that I think is very useful for an project like the kernel that has a fairly deep and well-separated directory structure with semantic meaning. What I mean by that is that it's often interesting to see exactly which sub-directories are impacted by a patch, and to what degree - even if you don't perhaps care so much about the individual files themselves. What makes the concept more interesting is that the "impact" is often hierarchical: in the kernel, for example, something could either have a very localized impact to "fs/ext3/" and then it's interesting to see that such a patch changes mostly that subdirectory, but you could have another patch that changes some generic VFS-layer issue which affects _many_ subdirectories that are all under "fs/", but none - or perhaps just a couple of them - of the individual filesystems are interesting in themselves. So what commonly happens is that you may have big changes in a specific sub-subdirectory, but still also significant separate changes to the subdirectory leading up to that - maybe you have significant VFS-level changes, but *also* changes under that VFS layer in the NFS-specific directories, for example. In that case, you do want the low-level parts that are significant to show up, but then the insignificant ones should show up as under the more generic top-level directory. This patch shows all of that with "--dirstat". The output can be either something simple like commit 81772fe... Author: Thomas Gleixner <tglx@linutronix.de> Date: Sun Feb 10 23:57:36 2008 +0100 x86: remove over noisy debug printk pageattr-test.c contains a noisy debug printk that people reported. The condition under which it prints (randomly tapping into a mem_map[] hole and not being able to c_p_a() there) is valid behavior and not interesting to report. Remove it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 100.0% arch/x86/mm/ or something much more complex like commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 15.3% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ where that latter example is an example of significant work in some individual fs/*/ subdirectories (like the patches to reiserfs accounting for 7.6% of the whole), but then discounting those individual filesystems, there's also 15.3% other "random" things that weren't worth reporting on their oen left over under fs/ in general (either in that directory itself, or in subdirectories of fs/ that didn't have enough changes to be reported individually). I'd like to stress that the "15.3% fs/" mentioned above is the stuff that is under fs/ but that was _not_ significant enough to report on its own. So the above does _not_ mean that 15.3% of the work was under fs/ per se, because that 15.3% does *not* include the already-reported 7.6% of afs, 7.6% of fuse etc. If you want to enable "cumulative" directory statistics, you can use the "--cumulative" flag, which adds up percentages recursively even when they have been already reported for a sub-directory. That cumulative output is disabled if *all* of the changes in one subdirectory come from a deeper subdirectory, to avoid repeating subdirectories all the way to the root. For an example of the cumulative reporting, the above commit becomes commit e231c2e... Author: David Howells <dhowells@redhat.com> Date: Thu Feb 7 00:15:26 2008 -0800 Convert ERR_PTR(PTR_ERR(p)) instances to ERR_CAST(p) 20.5% crypto/ 7.6% fs/afs/ 7.6% fs/fuse/ 7.6% fs/gfs2/ 5.1% fs/jffs2/ 5.1% fs/nfs/ 5.1% fs/nfsd/ 7.6% fs/reiserfs/ 61.5% fs/ 7.6% net/rxrpc/ 10.2% security/keys/ in which the commit percentages now obviously add up to much more than 100%: now the changes that were already reported for the sub-directories under fs/ are then cumulatively included in the whole percentage of fs/ (ie now shows 61.5% as opposed to the 15.3% without the cumulative reporting). The default reporting limit has been arbitrarily set at 3%, which seems to be a pretty good cut-off, but you can specify the cut-off manually by giving it as an option parameter (eg "--dirstat=5" makes the cut-off be at 5% instead) NOTE! The percentages are purely about the total lines added and removed, not anything smarter (or dumber) than that. Also note that you should not generally expect things to add up to 100%: not only does it round down, we don't report leftover scraps (they add up to the top-level change count, but we don't even bother reporting that, it only reports subdirectories). Quite frankly, as a top-level manager this is really convenient for me, but it's going to be very boring for git itself since there are few subdirectories. Also, don't expect things to make tons of sense if you combine this with "-M" and there are cross-directory renames etc. But even for git itself, you can get some fun statistics. Try out git log --dirstat and see the occasional mentions of things like Documentation/, git-gui/, gitweb/ and gitk-git/. Or try out something like git diff --dirstat v1.5.0..v1.5.4 which does kind of git an overview that shows *something*. But in general, the output is more exciting for big projects with deeper structure, and doing a git diff --dirstat v2.6.24..v2.6.25-rc1 on the kernel is what I actually wrote this for! Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 05:26:31 +08:00
else if (opt_arg(arg, 'X', "dirstat", &options->dirstat_percent))
options->output_format |= DIFF_FORMAT_DIRSTAT;
else if (!strcmp(arg, "--cumulative")) {
options->output_format |= DIFF_FORMAT_DIRSTAT;
DIFF_OPT_SET(options, DIRSTAT_CUMULATIVE);
} else if (opt_arg(arg, 0, "dirstat-by-file",
&options->dirstat_percent)) {
options->output_format |= DIFF_FORMAT_DIRSTAT;
DIFF_OPT_SET(options, DIRSTAT_BY_FILE);
}
else if (!strcmp(arg, "--check"))
options->output_format |= DIFF_FORMAT_CHECKDIFF;
else if (!strcmp(arg, "--summary"))
options->output_format |= DIFF_FORMAT_SUMMARY;
else if (!strcmp(arg, "--patch-with-stat"))
options->output_format |= DIFF_FORMAT_PATCH | DIFF_FORMAT_DIFFSTAT;
else if (!strcmp(arg, "--name-only"))
options->output_format |= DIFF_FORMAT_NAME;
else if (!strcmp(arg, "--name-status"))
options->output_format |= DIFF_FORMAT_NAME_STATUS;
else if (!strcmp(arg, "-s"))
options->output_format |= DIFF_FORMAT_NO_OUTPUT;
else if (!prefixcmp(arg, "--stat")) {
char *end;
int width = options->stat_width;
int name_width = options->stat_name_width;
arg += 6;
end = (char *)arg;
switch (*arg) {
case '-':
if (!prefixcmp(arg, "-width="))
width = strtoul(arg + 7, &end, 10);
else if (!prefixcmp(arg, "-name-width="))
name_width = strtoul(arg + 12, &end, 10);
break;
case '=':
width = strtoul(arg+1, &end, 10);
if (*end == ',')
name_width = strtoul(end+1, &end, 10);
}
/* Important! This checks all the error cases! */
if (*end)
return 0;
options->output_format |= DIFF_FORMAT_DIFFSTAT;
options->stat_name_width = name_width;
options->stat_width = width;
}
/* renames options */
else if (!prefixcmp(arg, "-B")) {
if ((options->break_opt = diff_scoreopt_parse(arg)) == -1)
return -1;
}
else if (!prefixcmp(arg, "-M")) {
if ((options->rename_score = diff_scoreopt_parse(arg)) == -1)
return -1;
options->detect_rename = DIFF_DETECT_RENAME;
}
else if (!prefixcmp(arg, "-C")) {
if (options->detect_rename == DIFF_DETECT_COPY)
DIFF_OPT_SET(options, FIND_COPIES_HARDER);
if ((options->rename_score = diff_scoreopt_parse(arg)) == -1)
return -1;
options->detect_rename = DIFF_DETECT_COPY;
}
else if (!strcmp(arg, "--no-renames"))
options->detect_rename = 0;
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
else if (!strcmp(arg, "--relative"))
DIFF_OPT_SET(options, RELATIVE_NAME);
else if (!prefixcmp(arg, "--relative=")) {
DIFF_OPT_SET(options, RELATIVE_NAME);
options->prefix = arg + 11;
}
/* xdiff options */
else if (!strcmp(arg, "-w") || !strcmp(arg, "--ignore-all-space"))
DIFF_XDL_SET(options, IGNORE_WHITESPACE);
else if (!strcmp(arg, "-b") || !strcmp(arg, "--ignore-space-change"))
DIFF_XDL_SET(options, IGNORE_WHITESPACE_CHANGE);
else if (!strcmp(arg, "--ignore-space-at-eol"))
DIFF_XDL_SET(options, IGNORE_WHITESPACE_AT_EOL);
else if (!strcmp(arg, "--patience"))
DIFF_XDL_SET(options, PATIENCE_DIFF);
/* flags options */
else if (!strcmp(arg, "--binary")) {
options->output_format |= DIFF_FORMAT_PATCH;
DIFF_OPT_SET(options, BINARY);
}
else if (!strcmp(arg, "--full-index"))
DIFF_OPT_SET(options, FULL_INDEX);
else if (!strcmp(arg, "-a") || !strcmp(arg, "--text"))
DIFF_OPT_SET(options, TEXT);
else if (!strcmp(arg, "-R"))
DIFF_OPT_SET(options, REVERSE_DIFF);
else if (!strcmp(arg, "--find-copies-harder"))
DIFF_OPT_SET(options, FIND_COPIES_HARDER);
Finally implement "git log --follow" Ok, I've really held off doing this too damn long, because I'm lazy, and I was always hoping that somebody else would do it. But no, people keep asking for it, but nobody actually did anything, so I decided I might as well bite the bullet, and instead of telling people they could add a "--follow" flag to "git log" to do what they want to do, I decided that it looks like I just have to do it for them.. The code wasn't actually that complicated, in that the diffstat for this patch literally says "70 insertions(+), 1 deletions(-)", but I will have to admit that in order to get to this fairly simple patch, you did have to know and understand the internal git diff generation machinery pretty well, and had to really be able to follow how commit generation interacts with generating patches and generating the log. So I suspect that while I was right that it wasn't that hard, I might have been expecting too much of random people - this patch does seem to be firmly in the core "Linus or Junio" territory. To make a long story short: I'm sorry for it taking so long until I just did it. I'm not going to guarantee that this works for everybody, but you really can just look at the patch, and after the appropriate appreciative noises ("Ooh, aah") over how clever I am, you can then just notice that the code itself isn't really that complicated. All the real new code is in the new "try_to_follow_renames()" function. It really isn't rocket science: we notice that the pathname we were looking at went away, so we start a full tree diff and try to see if we can instead make that pathname be a rename or a copy from some other previous pathname. And if we can, we just continue, except we show *that* particular diff, and ever after we use the _previous_ pathname. One thing to look out for: the "rename detection" is considered to be a singular event in the _linear_ "git log" output! That's what people want to do, but I just wanted to point out that this patch is *not* carrying around a "commit,pathname" kind of pair and it's *not* going to be able to notice the file coming from multiple *different* files in earlier history. IOW, if you use "git log --follow", then you get the stupid CVS/SVN kind of "files have single identities" kind of semantics, and git log will just pick the identity based on the normal move/copy heuristics _as_if_ the history could be linearized. Put another way: I think the model is broken, but given the broken model, I think this patch does just about as well as you can do. If you have merges with the same "file" having different filenames over the two branches, git will just end up picking _one_ of the pathnames at the point where the newer one goes away. It never looks at multiple pathnames in parallel. And if you understood all that, you probably didn't need it explained, and if you didn't understand the above blathering, it doesn't really mtter to you. What matters to you is that you can now do git log -p --follow builtin-rev-list.c and it will find the point where the old "rev-list.c" got renamed to "builtin-rev-list.c" and show it as such. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-20 05:22:46 +08:00
else if (!strcmp(arg, "--follow"))
DIFF_OPT_SET(options, FOLLOW_RENAMES);
else if (!strcmp(arg, "--color"))
DIFF_OPT_SET(options, COLOR_DIFF);
else if (!strcmp(arg, "--no-color"))
DIFF_OPT_CLR(options, COLOR_DIFF);
else if (!strcmp(arg, "--color-words")) {
DIFF_OPT_SET(options, COLOR_DIFF);
DIFF_OPT_SET(options, COLOR_DIFF_WORDS);
}
else if (!prefixcmp(arg, "--color-words=")) {
DIFF_OPT_SET(options, COLOR_DIFF);
DIFF_OPT_SET(options, COLOR_DIFF_WORDS);
options->word_regex = arg + 14;
}
else if (!strcmp(arg, "--exit-code"))
DIFF_OPT_SET(options, EXIT_WITH_STATUS);
else if (!strcmp(arg, "--quiet"))
DIFF_OPT_SET(options, QUICK);
else if (!strcmp(arg, "--ext-diff"))
DIFF_OPT_SET(options, ALLOW_EXTERNAL);
else if (!strcmp(arg, "--no-ext-diff"))
DIFF_OPT_CLR(options, ALLOW_EXTERNAL);
else if (!strcmp(arg, "--textconv"))
DIFF_OPT_SET(options, ALLOW_TEXTCONV);
else if (!strcmp(arg, "--no-textconv"))
DIFF_OPT_CLR(options, ALLOW_TEXTCONV);
else if (!strcmp(arg, "--ignore-submodules"))
DIFF_OPT_SET(options, IGNORE_SUBMODULES);
else if (!strcmp(arg, "--submodule"))
DIFF_OPT_SET(options, SUBMODULE_LOG);
else if (!prefixcmp(arg, "--submodule=")) {
if (!strcmp(arg + 12, "log"))
DIFF_OPT_SET(options, SUBMODULE_LOG);
}
/* misc options */
else if (!strcmp(arg, "-z"))
options->line_termination = 0;
else if (!prefixcmp(arg, "-l"))
options->rename_limit = strtoul(arg+2, NULL, 10);
else if (!prefixcmp(arg, "-S"))
options->pickaxe = arg + 2;
else if (!strcmp(arg, "--pickaxe-all"))
options->pickaxe_opts = DIFF_PICKAXE_ALL;
else if (!strcmp(arg, "--pickaxe-regex"))
options->pickaxe_opts = DIFF_PICKAXE_REGEX;
else if (!prefixcmp(arg, "-O"))
options->orderfile = arg + 2;
else if (!prefixcmp(arg, "--diff-filter="))
options->filter = arg + 14;
else if (!strcmp(arg, "--abbrev"))
options->abbrev = DEFAULT_ABBREV;
else if (!prefixcmp(arg, "--abbrev=")) {
options->abbrev = strtoul(arg + 9, NULL, 10);
if (options->abbrev < MINIMUM_ABBREV)
options->abbrev = MINIMUM_ABBREV;
else if (40 < options->abbrev)
options->abbrev = 40;
}
else if (!prefixcmp(arg, "--src-prefix="))
options->a_prefix = arg + 13;
else if (!prefixcmp(arg, "--dst-prefix="))
options->b_prefix = arg + 13;
else if (!strcmp(arg, "--no-prefix"))
options->a_prefix = options->b_prefix = "";
else if (opt_arg(arg, '\0', "inter-hunk-context",
&options->interhunkcontext))
;
else if (!prefixcmp(arg, "--output=")) {
options->file = fopen(arg + strlen("--output="), "w");
options->close_file = 1;
} else
return 0;
return 1;
}
static int parse_num(const char **cp_p)
{
unsigned long num, scale;
int ch, dot;
const char *cp = *cp_p;
num = 0;
scale = 1;
dot = 0;
for (;;) {
ch = *cp;
if ( !dot && ch == '.' ) {
scale = 1;
dot = 1;
} else if ( ch == '%' ) {
scale = dot ? scale*100 : 100;
cp++; /* % is always at the end */
break;
} else if ( ch >= '0' && ch <= '9' ) {
if ( scale < 100000 ) {
scale *= 10;
num = (num*10) + (ch-'0');
}
} else {
break;
}
cp++;
}
*cp_p = cp;
/* user says num divided by scale and we say internally that
* is MAX_SCORE * num / scale.
*/
return (int)((num >= scale) ? MAX_SCORE : (MAX_SCORE * num / scale));
}
static int diff_scoreopt_parse(const char *opt)
{
int opt1, opt2, cmd;
if (*opt++ != '-')
return -1;
cmd = *opt++;
if (cmd != 'M' && cmd != 'C' && cmd != 'B')
return -1; /* that is not a -M, -C nor -B option */
opt1 = parse_num(&opt);
if (cmd != 'B')
opt2 = 0;
else {
if (*opt == 0)
opt2 = 0;
else if (*opt != '/')
return -1; /* we expect -B80/99 or -B80 */
else {
opt++;
opt2 = parse_num(&opt);
}
}
if (*opt != 0)
return -1;
return opt1 | (opt2 << 16);
}
struct diff_queue_struct diff_queued_diff;
void diff_q(struct diff_queue_struct *queue, struct diff_filepair *dp)
{
if (queue->alloc <= queue->nr) {
queue->alloc = alloc_nr(queue->alloc);
queue->queue = xrealloc(queue->queue,
sizeof(dp) * queue->alloc);
}
queue->queue[queue->nr++] = dp;
}
struct diff_filepair *diff_queue(struct diff_queue_struct *queue,
struct diff_filespec *one,
struct diff_filespec *two)
{
struct diff_filepair *dp = xcalloc(1, sizeof(*dp));
dp->one = one;
dp->two = two;
if (queue)
diff_q(queue, dp);
return dp;
}
void diff_free_filepair(struct diff_filepair *p)
{
free_filespec(p->one);
free_filespec(p->two);
free(p);
}
/* This is different from find_unique_abbrev() in that
* it stuffs the result with dots for alignment.
*/
const char *diff_unique_abbrev(const unsigned char *sha1, int len)
{
int abblen;
const char *abbrev;
if (len == 40)
return sha1_to_hex(sha1);
abbrev = find_unique_abbrev(sha1, len);
abblen = strlen(abbrev);
if (abblen < 37) {
static char hex[41];
if (len < abblen && abblen <= len + 2)
sprintf(hex, "%s%.*s", abbrev, len+3-abblen, "..");
else
sprintf(hex, "%s...", abbrev);
return hex;
}
return sha1_to_hex(sha1);
}
static void diff_flush_raw(struct diff_filepair *p, struct diff_options *opt)
{
int line_termination = opt->line_termination;
int inter_name_termination = line_termination ? '\t' : '\0';
if (!(opt->output_format & DIFF_FORMAT_NAME_STATUS)) {
fprintf(opt->file, ":%06o %06o %s ", p->one->mode, p->two->mode,
diff_unique_abbrev(p->one->sha1, opt->abbrev));
fprintf(opt->file, "%s ", diff_unique_abbrev(p->two->sha1, opt->abbrev));
}
if (p->score) {
fprintf(opt->file, "%c%03d%c", p->status, similarity_index(p),
inter_name_termination);
} else {
fprintf(opt->file, "%c%c", p->status, inter_name_termination);
}
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
if (p->status == DIFF_STATUS_COPIED ||
p->status == DIFF_STATUS_RENAMED) {
const char *name_a, *name_b;
name_a = p->one->path;
name_b = p->two->path;
strip_prefix(opt->prefix_length, &name_a, &name_b);
write_name_quoted(name_a, opt->file, inter_name_termination);
write_name_quoted(name_b, opt->file, line_termination);
} else {
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
const char *name_a, *name_b;
name_a = p->one->mode ? p->one->path : p->two->path;
name_b = NULL;
strip_prefix(opt->prefix_length, &name_a, &name_b);
write_name_quoted(name_a, opt->file, line_termination);
}
}
int diff_unmodified_pair(struct diff_filepair *p)
{
/* This function is written stricter than necessary to support
* the currently implemented transformers, but the idea is to
* let transformers to produce diff_filepairs any way they want,
* and filter and clean them up here before producing the output.
*/
struct diff_filespec *one = p->one, *two = p->two;
if (DIFF_PAIR_UNMERGED(p))
return 0; /* unmerged is interesting */
/* deletion, addition, mode or type change
* and rename are all interesting.
*/
if (DIFF_FILE_VALID(one) != DIFF_FILE_VALID(two) ||
DIFF_PAIR_MODE_CHANGED(p) ||
strcmp(one->path, two->path))
return 0;
/* both are valid and point at the same path. that is, we are
* dealing with a change.
*/
if (one->sha1_valid && two->sha1_valid &&
!hashcmp(one->sha1, two->sha1))
return 1; /* no change */
if (!one->sha1_valid && !two->sha1_valid)
return 1; /* both look at the same file on the filesystem. */
return 0;
}
static void diff_flush_patch(struct diff_filepair *p, struct diff_options *o)
{
if (diff_unmodified_pair(p))
return;
if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
(DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
return; /* no tree diffs in patch format */
run_diff(p, o);
}
static void diff_flush_stat(struct diff_filepair *p, struct diff_options *o,
struct diffstat_t *diffstat)
{
if (diff_unmodified_pair(p))
return;
if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
(DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
return; /* no tree diffs in patch format */
run_diffstat(p, o, diffstat);
}
static void diff_flush_checkdiff(struct diff_filepair *p,
struct diff_options *o)
{
if (diff_unmodified_pair(p))
return;
if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
(DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
return; /* no tree diffs in patch format */
run_checkdiff(p, o);
}
int diff_queue_is_empty(void)
{
struct diff_queue_struct *q = &diff_queued_diff;
int i;
for (i = 0; i < q->nr; i++)
if (!diff_unmodified_pair(q->queue[i]))
return 0;
return 1;
}
#if DIFF_DEBUG
void diff_debug_filespec(struct diff_filespec *s, int x, const char *one)
{
fprintf(stderr, "queue[%d] %s (%s) %s %06o %s\n",
x, one ? one : "",
s->path,
DIFF_FILE_VALID(s) ? "valid" : "invalid",
s->mode,
s->sha1_valid ? sha1_to_hex(s->sha1) : "");
fprintf(stderr, "queue[%d] %s size %lu flags %d\n",
x, one ? one : "",
s->size, s->xfrm_flags);
}
void diff_debug_filepair(const struct diff_filepair *p, int i)
{
diff_debug_filespec(p->one, i, "one");
diff_debug_filespec(p->two, i, "two");
fprintf(stderr, "score %d, status %c rename_used %d broken %d\n",
p->score, p->status ? p->status : '?',
p->one->rename_used, p->broken_pair);
}
void diff_debug_queue(const char *msg, struct diff_queue_struct *q)
{
int i;
if (msg)
fprintf(stderr, "%s\n", msg);
fprintf(stderr, "q->nr = %d\n", q->nr);
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
diff_debug_filepair(p, i);
}
}
#endif
static void diff_resolve_rename_copy(void)
{
int i;
struct diff_filepair *p;
struct diff_queue_struct *q = &diff_queued_diff;
diff_debug_queue("resolve-rename-copy", q);
for (i = 0; i < q->nr; i++) {
p = q->queue[i];
p->status = 0; /* undecided */
if (DIFF_PAIR_UNMERGED(p))
p->status = DIFF_STATUS_UNMERGED;
else if (!DIFF_FILE_VALID(p->one))
p->status = DIFF_STATUS_ADDED;
else if (!DIFF_FILE_VALID(p->two))
p->status = DIFF_STATUS_DELETED;
else if (DIFF_PAIR_TYPE_CHANGED(p))
p->status = DIFF_STATUS_TYPE_CHANGED;
/* from this point on, we are dealing with a pair
* whose both sides are valid and of the same type, i.e.
* either in-place edit or rename/copy edit.
*/
else if (DIFF_PAIR_RENAME(p)) {
/*
* A rename might have re-connected a broken
* pair up, causing the pathnames to be the
* same again. If so, that's not a rename at
* all, just a modification..
*
* Otherwise, see if this source was used for
* multiple renames, in which case we decrement
* the count, and call it a copy.
*/
if (!strcmp(p->one->path, p->two->path))
p->status = DIFF_STATUS_MODIFIED;
else if (--p->one->rename_used > 0)
p->status = DIFF_STATUS_COPIED;
else
p->status = DIFF_STATUS_RENAMED;
}
else if (hashcmp(p->one->sha1, p->two->sha1) ||
p->one->mode != p->two->mode ||
is_null_sha1(p->one->sha1))
p->status = DIFF_STATUS_MODIFIED;
else {
/* This is a "no-change" entry and should not
* happen anymore, but prepare for broken callers.
*/
error("feeding unmodified %s to diffcore",
p->one->path);
p->status = DIFF_STATUS_UNKNOWN;
}
}
diff_debug_queue("resolve-rename-copy done", q);
}
static int check_pair_status(struct diff_filepair *p)
{
switch (p->status) {
case DIFF_STATUS_UNKNOWN:
return 0;
case 0:
die("internal error in diff-resolve-rename-copy");
default:
return 1;
}
}
static void flush_one_pair(struct diff_filepair *p, struct diff_options *opt)
{
int fmt = opt->output_format;
if (fmt & DIFF_FORMAT_CHECKDIFF)
diff_flush_checkdiff(p, opt);
else if (fmt & (DIFF_FORMAT_RAW | DIFF_FORMAT_NAME_STATUS))
diff_flush_raw(p, opt);
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
else if (fmt & DIFF_FORMAT_NAME) {
const char *name_a, *name_b;
name_a = p->two->path;
name_b = NULL;
strip_prefix(opt->prefix_length, &name_a, &name_b);
write_name_quoted(name_a, opt->file, opt->line_termination);
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
}
}
static void show_file_mode_name(FILE *file, const char *newdelete, struct diff_filespec *fs)
{
if (fs->mode)
fprintf(file, " %s mode %06o ", newdelete, fs->mode);
else
fprintf(file, " %s ", newdelete);
write_name_quoted(fs->path, file, '\n');
}
static void show_mode_change(FILE *file, struct diff_filepair *p, int show_name)
{
if (p->one->mode && p->two->mode && p->one->mode != p->two->mode) {
fprintf(file, " mode change %06o => %06o%c", p->one->mode, p->two->mode,
show_name ? ' ' : '\n');
if (show_name) {
write_name_quoted(p->two->path, file, '\n');
}
}
}
static void show_rename_copy(FILE *file, const char *renamecopy, struct diff_filepair *p)
{
char *names = pprint_rename(p->one->path, p->two->path);
fprintf(file, " %s %s (%d%%)\n", renamecopy, names, similarity_index(p));
free(names);
show_mode_change(file, p, 0);
}
static void diff_summary(FILE *file, struct diff_filepair *p)
{
switch(p->status) {
case DIFF_STATUS_DELETED:
show_file_mode_name(file, "delete", p->one);
break;
case DIFF_STATUS_ADDED:
show_file_mode_name(file, "create", p->two);
break;
case DIFF_STATUS_COPIED:
show_rename_copy(file, "copy", p);
break;
case DIFF_STATUS_RENAMED:
show_rename_copy(file, "rename", p);
break;
default:
if (p->score) {
fputs(" rewrite ", file);
write_name_quoted(p->two->path, file, ' ');
fprintf(file, "(%d%%)\n", similarity_index(p));
}
show_mode_change(file, p, !p->score);
break;
}
}
struct patch_id_t {
fix openssl headers conflicting with custom SHA1 implementations On ARM I have the following compilation errors: CC fast-import.o In file included from cache.h:8, from builtin.h:6, from fast-import.c:142: arm/sha1.h:14: error: conflicting types for 'SHA_CTX' /usr/include/openssl/sha.h:105: error: previous declaration of 'SHA_CTX' was here arm/sha1.h:16: error: conflicting types for 'SHA1_Init' /usr/include/openssl/sha.h:115: error: previous declaration of 'SHA1_Init' was here arm/sha1.h:17: error: conflicting types for 'SHA1_Update' /usr/include/openssl/sha.h:116: error: previous declaration of 'SHA1_Update' was here arm/sha1.h:18: error: conflicting types for 'SHA1_Final' /usr/include/openssl/sha.h:117: error: previous declaration of 'SHA1_Final' was here make: *** [fast-import.o] Error 1 This is because openssl header files are always included in git-compat-util.h since commit 684ec6c63c whenever NO_OPENSSL is not set, which somehow brings in <openssl/sha1.h> clashing with the custom ARM version. Compilation of git is probably broken on PPC too for the same reason. Turns out that the only file requiring openssl/ssl.h and openssl/err.h is imap-send.c. But only moving those problematic includes there doesn't solve the issue as it also includes cache.h which brings in the conflicting local SHA1 header file. As suggested by Jeff King, the best solution is to rename our references to SHA1 functions and structure to something git specific, and define those according to the implementation used. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-02 02:05:20 +08:00
git_SHA_CTX *ctx;
int patchlen;
};
static int remove_space(char *line, int len)
{
int i;
char *dst = line;
unsigned char c;
for (i = 0; i < len; i++)
if (!isspace((c = line[i])))
*dst++ = c;
return dst - line;
}
static void patch_id_consume(void *priv, char *line, unsigned long len)
{
struct patch_id_t *data = priv;
int new_len;
/* Ignore line numbers when computing the SHA1 of the patch */
if (!prefixcmp(line, "@@ -"))
return;
new_len = remove_space(line, len);
fix openssl headers conflicting with custom SHA1 implementations On ARM I have the following compilation errors: CC fast-import.o In file included from cache.h:8, from builtin.h:6, from fast-import.c:142: arm/sha1.h:14: error: conflicting types for 'SHA_CTX' /usr/include/openssl/sha.h:105: error: previous declaration of 'SHA_CTX' was here arm/sha1.h:16: error: conflicting types for 'SHA1_Init' /usr/include/openssl/sha.h:115: error: previous declaration of 'SHA1_Init' was here arm/sha1.h:17: error: conflicting types for 'SHA1_Update' /usr/include/openssl/sha.h:116: error: previous declaration of 'SHA1_Update' was here arm/sha1.h:18: error: conflicting types for 'SHA1_Final' /usr/include/openssl/sha.h:117: error: previous declaration of 'SHA1_Final' was here make: *** [fast-import.o] Error 1 This is because openssl header files are always included in git-compat-util.h since commit 684ec6c63c whenever NO_OPENSSL is not set, which somehow brings in <openssl/sha1.h> clashing with the custom ARM version. Compilation of git is probably broken on PPC too for the same reason. Turns out that the only file requiring openssl/ssl.h and openssl/err.h is imap-send.c. But only moving those problematic includes there doesn't solve the issue as it also includes cache.h which brings in the conflicting local SHA1 header file. As suggested by Jeff King, the best solution is to rename our references to SHA1 functions and structure to something git specific, and define those according to the implementation used. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-02 02:05:20 +08:00
git_SHA1_Update(data->ctx, line, new_len);
data->patchlen += new_len;
}
/* returns 0 upon success, and writes result into sha1 */
static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
{
struct diff_queue_struct *q = &diff_queued_diff;
int i;
fix openssl headers conflicting with custom SHA1 implementations On ARM I have the following compilation errors: CC fast-import.o In file included from cache.h:8, from builtin.h:6, from fast-import.c:142: arm/sha1.h:14: error: conflicting types for 'SHA_CTX' /usr/include/openssl/sha.h:105: error: previous declaration of 'SHA_CTX' was here arm/sha1.h:16: error: conflicting types for 'SHA1_Init' /usr/include/openssl/sha.h:115: error: previous declaration of 'SHA1_Init' was here arm/sha1.h:17: error: conflicting types for 'SHA1_Update' /usr/include/openssl/sha.h:116: error: previous declaration of 'SHA1_Update' was here arm/sha1.h:18: error: conflicting types for 'SHA1_Final' /usr/include/openssl/sha.h:117: error: previous declaration of 'SHA1_Final' was here make: *** [fast-import.o] Error 1 This is because openssl header files are always included in git-compat-util.h since commit 684ec6c63c whenever NO_OPENSSL is not set, which somehow brings in <openssl/sha1.h> clashing with the custom ARM version. Compilation of git is probably broken on PPC too for the same reason. Turns out that the only file requiring openssl/ssl.h and openssl/err.h is imap-send.c. But only moving those problematic includes there doesn't solve the issue as it also includes cache.h which brings in the conflicting local SHA1 header file. As suggested by Jeff King, the best solution is to rename our references to SHA1 functions and structure to something git specific, and define those according to the implementation used. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-02 02:05:20 +08:00
git_SHA_CTX ctx;
struct patch_id_t data;
char buffer[PATH_MAX * 4 + 20];
fix openssl headers conflicting with custom SHA1 implementations On ARM I have the following compilation errors: CC fast-import.o In file included from cache.h:8, from builtin.h:6, from fast-import.c:142: arm/sha1.h:14: error: conflicting types for 'SHA_CTX' /usr/include/openssl/sha.h:105: error: previous declaration of 'SHA_CTX' was here arm/sha1.h:16: error: conflicting types for 'SHA1_Init' /usr/include/openssl/sha.h:115: error: previous declaration of 'SHA1_Init' was here arm/sha1.h:17: error: conflicting types for 'SHA1_Update' /usr/include/openssl/sha.h:116: error: previous declaration of 'SHA1_Update' was here arm/sha1.h:18: error: conflicting types for 'SHA1_Final' /usr/include/openssl/sha.h:117: error: previous declaration of 'SHA1_Final' was here make: *** [fast-import.o] Error 1 This is because openssl header files are always included in git-compat-util.h since commit 684ec6c63c whenever NO_OPENSSL is not set, which somehow brings in <openssl/sha1.h> clashing with the custom ARM version. Compilation of git is probably broken on PPC too for the same reason. Turns out that the only file requiring openssl/ssl.h and openssl/err.h is imap-send.c. But only moving those problematic includes there doesn't solve the issue as it also includes cache.h which brings in the conflicting local SHA1 header file. As suggested by Jeff King, the best solution is to rename our references to SHA1 functions and structure to something git specific, and define those according to the implementation used. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-02 02:05:20 +08:00
git_SHA1_Init(&ctx);
memset(&data, 0, sizeof(struct patch_id_t));
data.ctx = &ctx;
for (i = 0; i < q->nr; i++) {
xpparam_t xpp;
xdemitconf_t xecfg;
xdemitcb_t ecb;
mmfile_t mf1, mf2;
struct diff_filepair *p = q->queue[i];
int len1, len2;
memset(&xpp, 0, sizeof(xpp));
memset(&xecfg, 0, sizeof(xecfg));
if (p->status == 0)
return error("internal diff status error");
if (p->status == DIFF_STATUS_UNKNOWN)
continue;
if (diff_unmodified_pair(p))
continue;
if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
(DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
continue;
if (DIFF_PAIR_UNMERGED(p))
continue;
diff_fill_sha1_info(p->one);
diff_fill_sha1_info(p->two);
if (fill_mmfile(&mf1, p->one) < 0 ||
fill_mmfile(&mf2, p->two) < 0)
return error("unable to read files to diff");
len1 = remove_space(p->one->path, strlen(p->one->path));
len2 = remove_space(p->two->path, strlen(p->two->path));
if (p->one->mode == 0)
len1 = snprintf(buffer, sizeof(buffer),
"diff--gita/%.*sb/%.*s"
"newfilemode%06o"
"---/dev/null"
"+++b/%.*s",
len1, p->one->path,
len2, p->two->path,
p->two->mode,
len2, p->two->path);
else if (p->two->mode == 0)
len1 = snprintf(buffer, sizeof(buffer),
"diff--gita/%.*sb/%.*s"
"deletedfilemode%06o"
"---a/%.*s"
"+++/dev/null",
len1, p->one->path,
len2, p->two->path,
p->one->mode,
len1, p->one->path);
else
len1 = snprintf(buffer, sizeof(buffer),
"diff--gita/%.*sb/%.*s"
"---a/%.*s"
"+++b/%.*s",
len1, p->one->path,
len2, p->two->path,
len1, p->one->path,
len2, p->two->path);
fix openssl headers conflicting with custom SHA1 implementations On ARM I have the following compilation errors: CC fast-import.o In file included from cache.h:8, from builtin.h:6, from fast-import.c:142: arm/sha1.h:14: error: conflicting types for 'SHA_CTX' /usr/include/openssl/sha.h:105: error: previous declaration of 'SHA_CTX' was here arm/sha1.h:16: error: conflicting types for 'SHA1_Init' /usr/include/openssl/sha.h:115: error: previous declaration of 'SHA1_Init' was here arm/sha1.h:17: error: conflicting types for 'SHA1_Update' /usr/include/openssl/sha.h:116: error: previous declaration of 'SHA1_Update' was here arm/sha1.h:18: error: conflicting types for 'SHA1_Final' /usr/include/openssl/sha.h:117: error: previous declaration of 'SHA1_Final' was here make: *** [fast-import.o] Error 1 This is because openssl header files are always included in git-compat-util.h since commit 684ec6c63c whenever NO_OPENSSL is not set, which somehow brings in <openssl/sha1.h> clashing with the custom ARM version. Compilation of git is probably broken on PPC too for the same reason. Turns out that the only file requiring openssl/ssl.h and openssl/err.h is imap-send.c. But only moving those problematic includes there doesn't solve the issue as it also includes cache.h which brings in the conflicting local SHA1 header file. As suggested by Jeff King, the best solution is to rename our references to SHA1 functions and structure to something git specific, and define those according to the implementation used. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-02 02:05:20 +08:00
git_SHA1_Update(&ctx, buffer, len1);
xpp.flags = XDF_NEED_MINIMAL;
xecfg.ctxlen = 3;
xecfg.flags = XDL_EMIT_FUNCNAMES;
xdi_diff_outf(&mf1, &mf2, patch_id_consume, &data,
&xpp, &xecfg, &ecb);
}
fix openssl headers conflicting with custom SHA1 implementations On ARM I have the following compilation errors: CC fast-import.o In file included from cache.h:8, from builtin.h:6, from fast-import.c:142: arm/sha1.h:14: error: conflicting types for 'SHA_CTX' /usr/include/openssl/sha.h:105: error: previous declaration of 'SHA_CTX' was here arm/sha1.h:16: error: conflicting types for 'SHA1_Init' /usr/include/openssl/sha.h:115: error: previous declaration of 'SHA1_Init' was here arm/sha1.h:17: error: conflicting types for 'SHA1_Update' /usr/include/openssl/sha.h:116: error: previous declaration of 'SHA1_Update' was here arm/sha1.h:18: error: conflicting types for 'SHA1_Final' /usr/include/openssl/sha.h:117: error: previous declaration of 'SHA1_Final' was here make: *** [fast-import.o] Error 1 This is because openssl header files are always included in git-compat-util.h since commit 684ec6c63c whenever NO_OPENSSL is not set, which somehow brings in <openssl/sha1.h> clashing with the custom ARM version. Compilation of git is probably broken on PPC too for the same reason. Turns out that the only file requiring openssl/ssl.h and openssl/err.h is imap-send.c. But only moving those problematic includes there doesn't solve the issue as it also includes cache.h which brings in the conflicting local SHA1 header file. As suggested by Jeff King, the best solution is to rename our references to SHA1 functions and structure to something git specific, and define those according to the implementation used. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-02 02:05:20 +08:00
git_SHA1_Final(sha1, &ctx);
return 0;
}
int diff_flush_patch_id(struct diff_options *options, unsigned char *sha1)
{
struct diff_queue_struct *q = &diff_queued_diff;
int i;
int result = diff_get_patch_id(options, sha1);
for (i = 0; i < q->nr; i++)
diff_free_filepair(q->queue[i]);
free(q->queue);
q->queue = NULL;
q->nr = q->alloc = 0;
return result;
}
static int is_summary_empty(const struct diff_queue_struct *q)
{
int i;
for (i = 0; i < q->nr; i++) {
const struct diff_filepair *p = q->queue[i];
switch (p->status) {
case DIFF_STATUS_DELETED:
case DIFF_STATUS_ADDED:
case DIFF_STATUS_COPIED:
case DIFF_STATUS_RENAMED:
return 0;
default:
if (p->score)
return 0;
if (p->one->mode && p->two->mode &&
p->one->mode != p->two->mode)
return 0;
break;
}
}
return 1;
}
void diff_flush(struct diff_options *options)
{
struct diff_queue_struct *q = &diff_queued_diff;
int i, output_format = options->output_format;
int separator = 0;
/*
* Order: raw, stat, summary, patch
* or: name/name-status/checkdiff (other bits clear)
*/
if (!q->nr)
goto free_queue;
if (output_format & (DIFF_FORMAT_RAW |
DIFF_FORMAT_NAME |
DIFF_FORMAT_NAME_STATUS |
DIFF_FORMAT_CHECKDIFF)) {
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
if (check_pair_status(p))
flush_one_pair(p, options);
}
separator++;
}
if (output_format & (DIFF_FORMAT_DIFFSTAT|DIFF_FORMAT_SHORTSTAT|DIFF_FORMAT_NUMSTAT)) {
struct diffstat_t diffstat;
memset(&diffstat, 0, sizeof(struct diffstat_t));
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
if (check_pair_status(p))
diff_flush_stat(p, options, &diffstat);
}
if (output_format & DIFF_FORMAT_NUMSTAT)
show_numstat(&diffstat, options);
if (output_format & DIFF_FORMAT_DIFFSTAT)
show_stats(&diffstat, options);
if (output_format & DIFF_FORMAT_SHORTSTAT)
show_shortstats(&diffstat, options);
free_diffstat_info(&diffstat);
separator++;
}
if (output_format & DIFF_FORMAT_DIRSTAT)
show_dirstat(options);
if (output_format & DIFF_FORMAT_SUMMARY && !is_summary_empty(q)) {
for (i = 0; i < q->nr; i++)
diff_summary(options->file, q->queue[i]);
separator++;
}
if (output_format & DIFF_FORMAT_PATCH) {
if (separator) {
putc(options->line_termination, options->file);
if (options->stat_sep) {
/* attach patch instead of inline */
fputs(options->stat_sep, options->file);
}
}
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
if (check_pair_status(p))
diff_flush_patch(p, options);
}
}
if (output_format & DIFF_FORMAT_CALLBACK)
options->format_callback(q, options, options->format_callback_data);
for (i = 0; i < q->nr; i++)
diff_free_filepair(q->queue[i]);
free_queue:
free(q->queue);
q->queue = NULL;
q->nr = q->alloc = 0;
if (options->close_file)
fclose(options->file);
/*
* Report the content-level differences with HAS_CHANGES;
* diff_addremove/diff_change does not set the bit when
* DIFF_FROM_CONTENTS is in effect (e.g. with -w).
*/
if (DIFF_OPT_TST(options, DIFF_FROM_CONTENTS)) {
if (options->found_changes)
DIFF_OPT_SET(options, HAS_CHANGES);
else
DIFF_OPT_CLR(options, HAS_CHANGES);
}
}
static void diffcore_apply_filter(const char *filter)
{
int i;
struct diff_queue_struct *q = &diff_queued_diff;
struct diff_queue_struct outq;
outq.queue = NULL;
outq.nr = outq.alloc = 0;
if (!filter)
return;
if (strchr(filter, DIFF_STATUS_FILTER_AON)) {
int found;
for (i = found = 0; !found && i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
if (((p->status == DIFF_STATUS_MODIFIED) &&
((p->score &&
strchr(filter, DIFF_STATUS_FILTER_BROKEN)) ||
(!p->score &&
strchr(filter, DIFF_STATUS_MODIFIED)))) ||
((p->status != DIFF_STATUS_MODIFIED) &&
strchr(filter, p->status)))
found++;
}
if (found)
return;
/* otherwise we will clear the whole queue
* by copying the empty outq at the end of this
* function, but first clear the current entries
* in the queue.
*/
for (i = 0; i < q->nr; i++)
diff_free_filepair(q->queue[i]);
}
else {
/* Only the matching ones */
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
if (((p->status == DIFF_STATUS_MODIFIED) &&
((p->score &&
strchr(filter, DIFF_STATUS_FILTER_BROKEN)) ||
(!p->score &&
strchr(filter, DIFF_STATUS_MODIFIED)))) ||
((p->status != DIFF_STATUS_MODIFIED) &&
strchr(filter, p->status)))
diff_q(&outq, p);
else
diff_free_filepair(p);
}
}
free(q->queue);
*q = outq;
}
/* Check whether two filespecs with the same mode and size are identical */
static int diff_filespec_is_identical(struct diff_filespec *one,
struct diff_filespec *two)
{
if (S_ISGITLINK(one->mode))
return 0;
if (diff_populate_filespec(one, 0))
return 0;
if (diff_populate_filespec(two, 0))
return 0;
return !memcmp(one->data, two->data, one->size);
}
static void diffcore_skip_stat_unmatch(struct diff_options *diffopt)
{
int i;
struct diff_queue_struct *q = &diff_queued_diff;
struct diff_queue_struct outq;
outq.queue = NULL;
outq.nr = outq.alloc = 0;
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
/*
* 1. Entries that come from stat info dirtyness
* always have both sides (iow, not create/delete),
* one side of the object name is unknown, with
* the same mode and size. Keep the ones that
* do not match these criteria. They have real
* differences.
*
* 2. At this point, the file is known to be modified,
* with the same mode and size, and the object
* name of one side is unknown. Need to inspect
* the identical contents.
*/
if (!DIFF_FILE_VALID(p->one) || /* (1) */
!DIFF_FILE_VALID(p->two) ||
(p->one->sha1_valid && p->two->sha1_valid) ||
(p->one->mode != p->two->mode) ||
diff_populate_filespec(p->one, 1) ||
diff_populate_filespec(p->two, 1) ||
(p->one->size != p->two->size) ||
!diff_filespec_is_identical(p->one, p->two)) /* (2) */
diff_q(&outq, p);
else {
/*
* The caller can subtract 1 from skip_stat_unmatch
* to determine how many paths were dirty only
* due to stat info mismatch.
*/
if (!DIFF_OPT_TST(diffopt, NO_INDEX))
diffopt->skip_stat_unmatch++;
diff_free_filepair(p);
}
}
free(q->queue);
*q = outq;
}
unpack-trees.c: look ahead in the index This makes the traversal of index be in sync with the tree traversal. When unpack_callback() is fed a set of tree entries from trees, it inspects the name of the entry and checks if the an index entry with the same name could be hiding behind the current index entry, and (1) if the name appears in the index as a leaf node, it is also fed to the n_way_merge() callback function; (2) if the name is a directory in the index, i.e. there are entries in that are underneath it, then nothing is fed to the n_way_merge() callback function; (3) otherwise, if the name comes before the first eligible entry in the index, the index entry is first unpacked alone. When traverse_trees_recursive() descends into a subdirectory, the cache_bottom pointer is moved to walk index entries within that directory. All of these are omitted for diff-index, which does not even want to be fed an index entry and a tree entry with D/F conflicts. This fixes 3-way read-tree and exposes a bug in other parts of the system in t6035, test #5. The test prepares these three trees: O = HEAD^ 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x A = HEAD 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob 587be6b4c3f93f93c489c0111bba5596147a26cb a/x B = master 120000 blob a36b77384451ea1de7bd340ffca868249626bc52 a/b 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x With a clean index that matches HEAD, running git read-tree -m -u --aggressive $O $A $B now yields 120000 a36b77384451ea1de7bd340ffca868249626bc52 3 a/b 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0 a/b-2/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 1 a/b/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 2 a/b/c/d 100644 587be6b4c3f93f93c489c0111bba5596147a26cb 0 a/x which is correct. "master" created "a/b" symlink that did not exist, and removed "a/b/c/d" while HEAD did not do touch either path. Before this series, read-tree did not notice the situation and resolved addition of "a/b" and removal of "a/b/c/d" independently. If A = HEAD had another path "a/b/c/e" added, this merge should conflict but instead it silently resolved "a/b" and then immediately overwrote it to add "a/b/c/e", which was quite bogus. Tests in t1012 start to work with this. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-09-20 15:03:39 +08:00
static int diffnamecmp(const void *a_, const void *b_)
{
const struct diff_filepair *a = *((const struct diff_filepair **)a_);
const struct diff_filepair *b = *((const struct diff_filepair **)b_);
const char *name_a, *name_b;
name_a = a->one ? a->one->path : a->two->path;
name_b = b->one ? b->one->path : b->two->path;
return strcmp(name_a, name_b);
}
void diffcore_fix_diff_index(struct diff_options *options)
{
struct diff_queue_struct *q = &diff_queued_diff;
qsort(q->queue, q->nr, sizeof(q->queue[0]), diffnamecmp);
}
void diffcore_std(struct diff_options *options)
{
if (options->skip_stat_unmatch)
diffcore_skip_stat_unmatch(options);
if (options->break_opt != -1)
diffcore_break(options->break_opt);
if (options->detect_rename)
diffcore_rename(options);
if (options->break_opt != -1)
diffcore_merge_broken();
if (options->pickaxe)
diffcore_pickaxe(options->pickaxe, options->pickaxe_opts);
if (options->orderfile)
diffcore_order(options->orderfile);
diff_resolve_rename_copy();
diffcore_apply_filter(options->filter);
if (diff_queued_diff.nr && !DIFF_OPT_TST(options, DIFF_FROM_CONTENTS))
DIFF_OPT_SET(options, HAS_CHANGES);
else
DIFF_OPT_CLR(options, HAS_CHANGES);
}
int diff_result_code(struct diff_options *opt, int status)
{
int result = 0;
if (!DIFF_OPT_TST(opt, EXIT_WITH_STATUS) &&
!(opt->output_format & DIFF_FORMAT_CHECKDIFF))
return status;
if (DIFF_OPT_TST(opt, EXIT_WITH_STATUS) &&
DIFF_OPT_TST(opt, HAS_CHANGES))
result |= 01;
if ((opt->output_format & DIFF_FORMAT_CHECKDIFF) &&
DIFF_OPT_TST(opt, CHECK_FAILED))
result |= 02;
return result;
}
void diff_addremove(struct diff_options *options,
int addremove, unsigned mode,
const unsigned char *sha1,
const char *concatpath, unsigned dirty_submodule)
{
struct diff_filespec *one, *two;
if (DIFF_OPT_TST(options, IGNORE_SUBMODULES) && S_ISGITLINK(mode))
return;
/* This may look odd, but it is a preparation for
* feeding "there are unchanged files which should
* not produce diffs, but when you are doing copy
* detection you would need them, so here they are"
* entries to the diff-core. They will be prefixed
* with something like '=' or '*' (I haven't decided
* which but should not make any difference).
* Feeding the same new and old to diff_change()
* also has the same effect.
* Before the final output happens, they are pruned after
* merged into rename/copy pairs as appropriate.
*/
if (DIFF_OPT_TST(options, REVERSE_DIFF))
addremove = (addremove == '+' ? '-' :
addremove == '-' ? '+' : addremove);
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
if (options->prefix &&
strncmp(concatpath, options->prefix, options->prefix_length))
return;
one = alloc_filespec(concatpath);
two = alloc_filespec(concatpath);
if (addremove != '+')
fill_filespec(one, sha1, mode);
if (addremove != '-') {
fill_filespec(two, sha1, mode);
two->dirty_submodule = dirty_submodule;
}
diff_queue(&diff_queued_diff, one, two);
if (!DIFF_OPT_TST(options, DIFF_FROM_CONTENTS))
DIFF_OPT_SET(options, HAS_CHANGES);
}
void diff_change(struct diff_options *options,
unsigned old_mode, unsigned new_mode,
const unsigned char *old_sha1,
const unsigned char *new_sha1,
const char *concatpath,
unsigned old_dirty_submodule, unsigned new_dirty_submodule)
{
struct diff_filespec *one, *two;
if (DIFF_OPT_TST(options, IGNORE_SUBMODULES) && S_ISGITLINK(old_mode)
&& S_ISGITLINK(new_mode))
return;
if (DIFF_OPT_TST(options, REVERSE_DIFF)) {
unsigned tmp;
const unsigned char *tmp_c;
tmp = old_mode; old_mode = new_mode; new_mode = tmp;
tmp_c = old_sha1; old_sha1 = new_sha1; new_sha1 = tmp_c;
tmp = old_dirty_submodule; old_dirty_submodule = new_dirty_submodule;
new_dirty_submodule = tmp;
}
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
if (options->prefix &&
strncmp(concatpath, options->prefix, options->prefix_length))
return;
one = alloc_filespec(concatpath);
two = alloc_filespec(concatpath);
fill_filespec(one, old_sha1, old_mode);
fill_filespec(two, new_sha1, new_mode);
one->dirty_submodule = old_dirty_submodule;
two->dirty_submodule = new_dirty_submodule;
diff_queue(&diff_queued_diff, one, two);
if (!DIFF_OPT_TST(options, DIFF_FROM_CONTENTS))
DIFF_OPT_SET(options, HAS_CHANGES);
}
void diff_unmerge(struct diff_options *options,
const char *path,
unsigned mode, const unsigned char *sha1)
{
struct diff_filespec *one, *two;
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 06:26:02 +08:00
if (options->prefix &&
strncmp(path, options->prefix, options->prefix_length))
return;
one = alloc_filespec(path);
two = alloc_filespec(path);
fill_filespec(one, sha1, mode);
diff_queue(&diff_queued_diff, one, two)->is_unmerged = 1;
}
static char *run_textconv(const char *pgm, struct diff_filespec *spec,
size_t *outsize)
{
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
struct diff_tempfile *temp;
const char *argv[3];
const char **arg = argv;
struct child_process child;
struct strbuf buf = STRBUF_INIT;
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
temp = prepare_temp_file(spec->path, spec);
*arg++ = pgm;
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
*arg++ = temp->name;
*arg = NULL;
memset(&child, 0, sizeof(child));
child.use_shell = 1;
child.argv = argv;
child.out = -1;
if (start_command(&child) != 0 ||
strbuf_read(&buf, child.out, 0) < 0 ||
finish_command(&child) != 0) {
close(child.out);
strbuf_release(&buf);
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
remove_tempfile();
error("error running textconv command '%s'", pgm);
return NULL;
}
close(child.out);
diff: refactor tempfile cleanup handling There are two pieces of code that create tempfiles for diff: run_external_diff and run_textconv. The former cleans up its tempfiles in the face of premature death (i.e., by die() or by signal), but the latter does not. After this patch, they will both use the same cleanup routines. To make clear what the change is, let me first explain what happens now: - run_external_diff uses a static global array of 2 diff_tempfile structs (since it knows it will always need exactly 2 tempfiles). It calls prepare_temp_file (which doesn't know anything about the global array) on each of the structs, creating the tempfiles that need to be cleaned up. It then registers atexit and signal handlers to look through the global array and remove the tempfiles. If it succeeds, it calls the handler manually (which marks the tempfile structs as unused). - textconv has its own tempfile struct, which it allocates using prepare_temp_file and cleans up manually. No signal or atexit handlers. The new code moves the installation of cleanup handlers into the prepare_temp_file function. Which means that that function now has to understand that there is static tempfile storage. So what happens now is: - run_external_diff calls prepare_temp_file - prepare_temp_file calls claim_diff_tempfile, which allocates an unused slot from our global array - prepare_temp_file installs (if they have not already been installed) atexit and signal handlers for cleanup - prepare_temp_file sets up the tempfile as usual - prepare_temp_file returns a pointer to the allocated tempfile The advantage being that run_external_diff no longer has to care about setting up cleanup handlers. Now by virtue of calling prepare_temp_file, run_textconv gets the same benefit, as will any future users of prepare_temp_file. There are also a few side benefits to the specific implementation: - we now install cleanup handlers _before_ allocating the tempfile, closing a race which could leave temp cruft - when allocating a slot in the global array, we will now detect a situation where the old slots were not properly vacated (i.e., somebody forgot to call remove upon leaving the function). In the old code, such a situation would silently overwrite the tempfile names, meaning we would forget to clean them up. The new code dies with a bug warning. - we make sure only to install the signal handler once. This isn't a big deal, since we are just overwriting the old handler, but will become an issue when a later patch converts the code to use sigchain Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-01-22 13:59:56 +08:00
remove_tempfile();
return strbuf_detach(&buf, outsize);
}