blob: 8d8405aba29a4240f6a68c5fb1e3f0ad15050318 [file] [log] [blame]
/*
* Copyright (C) 2005 Junio C Hamano
*/
#include "cache.h"
#include "quote.h"
#include "diff.h"
#include "diffcore.h"
#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"
#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 */
};
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;
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);
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;
};
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;
}
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 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;
}
}
static void remove_tempfile_on_signal(int signo)
{
remove_tempfile();
sigchain_pop(signo);
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;
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;
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;
int minus_first, minus_len, plus_first, plus_len;
const char *minus_begin, *minus_end, *plus_begin, *plus_end;
if (line[0] != '@' || parse_hunk_header(line, len,
&minus_first, &minus_len, &plus_first, &plus_len))
return;
/* 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;
}
/*
* 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)
{
int i, j;
long alloc = 0;
out->size = 0;
out->ptr = NULL;
/* 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;
/* 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);
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;
/* 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 */
xecfg.ctxlen = 0;
xdi_diff_outf(&minus, &plus, fn_out_diff_words_aux, diff_words,
&xpp, &xecfg, &ecb);
free(minus.ptr);
free(plus.ptr);
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;
}
/* 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) {
diff_words_flush(ecbdata);
free (ecbdata->diff_words->minus.text.ptr);
free (ecbdata->diff_words->minus.orig);
free (ecbdata->diff_words->plus.text.ptr);
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);
*(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] == '@') {
if (ecbdata->diff_words)
diff_words_flush(ecbdata);
len = sane_truncate_line(ecbdata, line, len);
find_lno(line, ecbdata);
emit_line(ecbdata->file,
diff_get_color(ecbdata->color_diff, DIFF_FRAGINFO),
reset, 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;
}
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;
};
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)
{
unsigned long this_dir = 0;
unsigned int sources = 0;
while (dir->nr) {
struct dirstat_file *f = dir->files;
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);
sources++;
} else {
this = f->changed;
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);
if (!dir->cumulative)
return 0;
}
}
}
return this_dir;
}
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)
{
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);
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++;
}
/* This can happen even with many files, if everything was renames */
if (!changed)
return;
/* Show all directories with more than x% of the changes */
qsort(dir.files, dir.nr, sizeof(dir.files[0]), dirstat_compare);
gather_dirstat(options->file, &dir, changed, "", 0);
}
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)
{
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;
}
static void emit_binary_diff_body(FILE *file, mmfile_t *one, mmfile_t *two)
{
void *cp;
void *delta;
void *deflated;
void *data;
unsigned long orig_size;
unsigned long delta_size;
unsigned long deflate_size;
unsigned long data_size;
/* We could do deflated delta, or we could do just deflated two,
* whichever is smaller.
*/
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);
}
}
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;
}
/* emit data encoded in base85 */
cp = data;
while (data_size) {
int bytes = (52 < data_size) ? 52 : data_size;
char line[70];
data_size -= bytes;
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);
}
fprintf(file, "\n");
free(data);
}
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)
{
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)
{
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_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,
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;
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;
}
/* 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";
fprintf(o->file, "%sdiff --git %s %s%s\n", set, a_one, b_two, reset);
if (lbl[0][0] == '/') {
/* /dev/null */
fprintf(o->file, "%snew file mode %06o%s\n", set, two->mode, reset);
if (xfrm_msg && xfrm_msg[0])
fprintf(o->file, "%s%s%s\n", set, xfrm_msg, reset);
}
else if (lbl[1][0] == '/') {
fprintf(o->file, "%sdeleted file mode %06o%s\n", set, one->mode, reset);
if (xfrm_msg && xfrm_msg[0])
fprintf(o->file, "%s%s%s\n", set, xfrm_msg, reset);
}
else {
if (one->mode != two->mode) {
fprintf(o->file, "%sold mode %06o%s\n", set, one->mode, reset);
fprintf(o->file, "%snew mode %06o%s\n", set, two->mode, reset);
}
if (xfrm_msg && xfrm_msg[0])
fprintf(o->file, "%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))) {
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;
if (DIFF_OPT_TST(o, BINARY))
emit_binary_diff(o->file, &mf1, &mf2);
else
fprintf(o->file, "Binary files %s and %s differ\n",
lbl[0], lbl[1]);
o->found_changes = 1;
}
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 (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;
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:
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 (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);
goto free_and_return;
}
if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
die("unable to read files to diff");
if (diff_filespec_is_binary(one) || diff_filespec_is_binary(two)) {
data->is_binary = 1;
data->added = mf2.size;
data->deleted = mf1.size;
} else {
/* Crazy xdl interfaces.. */
xpparam_t xpp;
xdemitconf_t xecfg;
xdemitcb_t ecb;
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);
}
free_and_return:
diff_free_filespec_data(one);
diff_free_filespec_data(two);
}
static void builtin_checkdiff(const char *name_a, const char *name_b,
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;
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;
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.
*/
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;
/* 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))
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)
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);
len = snprintf(data, 100,
"Subproject commit %s\n", sha1_to_hex(s->sha1));
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 ||
reuse_worktree_file(s->path, s->sha1, 0)) {
struct strbuf buf = STRBUF_INIT;
struct stat st;
int fd;
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;
/*
* Convert from working tree format to canonical git format
*/
if (convert_to_git(s->path, s->data, s->size, &buf, safe_crlf)) {
size_t size = 0;
munmap(s->data, s->size);
s->should_munmap = 0;
s->data = strbuf_detach(&buf, &size);
s->size = size;
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);
}
static struct diff_tempfile *prepare_temp_file(const char *name,
struct diff_filespec *one)
{
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, ".");
return temp;
}
if (!remove_tempfile_installed) {
atexit(remove_tempfile);
sigchain_push_common(remove_tempfile_on_signal);
remove_tempfile_installed = 1;
}
if (!one->sha1_valid ||
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);
}
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);
}
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) {
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;
*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, 0);
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,
const char *attr_path,
struct diff_filespec *one,
struct diff_filespec *two,
struct strbuf *msg,
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,
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);
}
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;
const char *attr_path;
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)) {
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);
run_diff_cmd(NULL, name, other, attr_path,
one, null, &msg, o, p);
free(null);
strbuf_release(&msg);
null = alloc_filespec(one->path);
run_diff_cmd(NULL, name, other, attr_path,
null, two, &msg, o, p);
free(null);
}
else
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);
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;
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);
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);
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;
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");
if (DIFF_OPT_TST(options, FIND_COPIES_HARDER))
options->detect_rename = DIFF_DETECT_COPY;
if (!DIFF_OPT_TST(options, RELATIVE_NAME))
options->prefix = NULL;