blob: 6a5ed216de3e68448e13c298a87aaf791fa15ffc [file] [log] [blame]
/*
* Copyright (C) 2005 Junio C Hamano
*/
#include "cache.h"
#include "config.h"
#include "tempfile.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 "object-store.h"
#include "userdiff.h"
#include "submodule-config.h"
#include "submodule.h"
#include "hashmap.h"
#include "mem-pool.h"
#include "ll-merge.h"
#include "string-list.h"
#include "strvec.h"
#include "graph.h"
#include "packfile.h"
#include "parse-options.h"
#include "help.h"
#include "promisor-remote.h"
#include "dir.h"
#include "strmap.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_indent_heuristic = 1;
static int diff_rename_limit_default = 1000;
static int diff_suppress_blank_empty;
static int diff_use_color_default = -1;
static int diff_color_moved_default;
static int diff_color_moved_ws_default;
static int diff_context_default = 3;
static int diff_interhunk_context_default;
static const char *diff_word_regex_cfg;
static const char *external_diff_cmd_cfg;
static const char *diff_order_file_cfg;
int diff_auto_refresh_index = 1;
static int diff_mnemonic_prefix;
static int diff_no_prefix;
static int diff_relative;
static int diff_stat_graph_width;
static int diff_dirstat_permille_default = 30;
static struct diff_options default_diff_options;
static long diff_algorithm;
static unsigned ws_error_highlight_default = WSEH_NEW;
static char diff_colors[][COLOR_MAXLEN] = {
GIT_COLOR_RESET,
GIT_COLOR_NORMAL, /* CONTEXT */
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 */
GIT_COLOR_BOLD_MAGENTA, /* OLD_MOVED */
GIT_COLOR_BOLD_BLUE, /* OLD_MOVED ALTERNATIVE */
GIT_COLOR_FAINT, /* OLD_MOVED_DIM */
GIT_COLOR_FAINT_ITALIC, /* OLD_MOVED_ALTERNATIVE_DIM */
GIT_COLOR_BOLD_CYAN, /* NEW_MOVED */
GIT_COLOR_BOLD_YELLOW, /* NEW_MOVED ALTERNATIVE */
GIT_COLOR_FAINT, /* NEW_MOVED_DIM */
GIT_COLOR_FAINT_ITALIC, /* NEW_MOVED_ALTERNATIVE_DIM */
GIT_COLOR_FAINT, /* CONTEXT_DIM */
GIT_COLOR_FAINT_RED, /* OLD_DIM */
GIT_COLOR_FAINT_GREEN, /* NEW_DIM */
GIT_COLOR_BOLD, /* CONTEXT_BOLD */
GIT_COLOR_BOLD_RED, /* OLD_BOLD */
GIT_COLOR_BOLD_GREEN, /* NEW_BOLD */
};
static const char *color_diff_slots[] = {
[DIFF_CONTEXT] = "context",
[DIFF_METAINFO] = "meta",
[DIFF_FRAGINFO] = "frag",
[DIFF_FILE_OLD] = "old",
[DIFF_FILE_NEW] = "new",
[DIFF_COMMIT] = "commit",
[DIFF_WHITESPACE] = "whitespace",
[DIFF_FUNCINFO] = "func",
[DIFF_FILE_OLD_MOVED] = "oldMoved",
[DIFF_FILE_OLD_MOVED_ALT] = "oldMovedAlternative",
[DIFF_FILE_OLD_MOVED_DIM] = "oldMovedDimmed",
[DIFF_FILE_OLD_MOVED_ALT_DIM] = "oldMovedAlternativeDimmed",
[DIFF_FILE_NEW_MOVED] = "newMoved",
[DIFF_FILE_NEW_MOVED_ALT] = "newMovedAlternative",
[DIFF_FILE_NEW_MOVED_DIM] = "newMovedDimmed",
[DIFF_FILE_NEW_MOVED_ALT_DIM] = "newMovedAlternativeDimmed",
[DIFF_CONTEXT_DIM] = "contextDimmed",
[DIFF_FILE_OLD_DIM] = "oldDimmed",
[DIFF_FILE_NEW_DIM] = "newDimmed",
[DIFF_CONTEXT_BOLD] = "contextBold",
[DIFF_FILE_OLD_BOLD] = "oldBold",
[DIFF_FILE_NEW_BOLD] = "newBold",
};
define_list_config_array_extra(color_diff_slots, {"plain"});
static int parse_diff_color_slot(const char *var)
{
if (!strcasecmp(var, "plain"))
return DIFF_CONTEXT;
return LOOKUP_CONFIG(color_diff_slots, var);
}
static int parse_dirstat_params(struct diff_options *options, const char *params_string,
struct strbuf *errmsg)
{
char *params_copy = xstrdup(params_string);
struct string_list params = STRING_LIST_INIT_NODUP;
int ret = 0;
int i;
if (*params_copy)
string_list_split_in_place(&params, params_copy, ',', -1);
for (i = 0; i < params.nr; i++) {
const char *p = params.items[i].string;
if (!strcmp(p, "changes")) {
options->flags.dirstat_by_line = 0;
options->flags.dirstat_by_file = 0;
} else if (!strcmp(p, "lines")) {
options->flags.dirstat_by_line = 1;
options->flags.dirstat_by_file = 0;
} else if (!strcmp(p, "files")) {
options->flags.dirstat_by_line = 0;
options->flags.dirstat_by_file = 1;
} else if (!strcmp(p, "noncumulative")) {
options->flags.dirstat_cumulative = 0;
} else if (!strcmp(p, "cumulative")) {
options->flags.dirstat_cumulative = 1;
} else if (isdigit(*p)) {
char *end;
int permille = strtoul(p, &end, 10) * 10;
if (*end == '.' && isdigit(*++end)) {
/* only use first digit */
permille += *end - '0';
/* .. and ignore any further digits */
while (isdigit(*++end))
; /* nothing */
}
if (!*end)
options->dirstat_permille = permille;
else {
strbuf_addf(errmsg, _(" Failed to parse dirstat cut-off percentage '%s'\n"),
p);
ret++;
}
} else {
strbuf_addf(errmsg, _(" Unknown dirstat parameter '%s'\n"), p);
ret++;
}
}
string_list_clear(&params, 0);
free(params_copy);
return ret;
}
static int parse_submodule_params(struct diff_options *options, const char *value)
{
if (!strcmp(value, "log"))
options->submodule_format = DIFF_SUBMODULE_LOG;
else if (!strcmp(value, "short"))
options->submodule_format = DIFF_SUBMODULE_SHORT;
else if (!strcmp(value, "diff"))
options->submodule_format = DIFF_SUBMODULE_INLINE_DIFF;
/*
* Please update $__git_diff_submodule_formats in
* git-completion.bash when you add new formats.
*/
else
return -1;
return 0;
}
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;
}
long parse_algorithm_value(const char *value)
{
if (!value)
return -1;
else if (!strcasecmp(value, "myers") || !strcasecmp(value, "default"))
return 0;
else if (!strcasecmp(value, "minimal"))
return XDF_NEED_MINIMAL;
else if (!strcasecmp(value, "patience"))
return XDF_PATIENCE_DIFF;
else if (!strcasecmp(value, "histogram"))
return XDF_HISTOGRAM_DIFF;
/*
* Please update $__git_diff_algorithms in git-completion.bash
* when you add new algorithms.
*/
return -1;
}
static int parse_one_token(const char **arg, const char *token)
{
const char *rest;
if (skip_prefix(*arg, token, &rest) && (!*rest || *rest == ',')) {
*arg = rest;
return 1;
}
return 0;
}
static int parse_ws_error_highlight(const char *arg)
{
const char *orig_arg = arg;
unsigned val = 0;
while (*arg) {
if (parse_one_token(&arg, "none"))
val = 0;
else if (parse_one_token(&arg, "default"))
val = WSEH_NEW;
else if (parse_one_token(&arg, "all"))
val = WSEH_NEW | WSEH_OLD | WSEH_CONTEXT;
else if (parse_one_token(&arg, "new"))
val |= WSEH_NEW;
else if (parse_one_token(&arg, "old"))
val |= WSEH_OLD;
else if (parse_one_token(&arg, "context"))
val |= WSEH_CONTEXT;
else {
return -1 - (int)(arg - orig_arg);
}
if (*arg)
arg++;
}
return val;
}
/*
* 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.
*/
void init_diff_ui_defaults(void)
{
diff_detect_rename_default = DIFF_DETECT_RENAME;
}
int git_diff_heuristic_config(const char *var, const char *value,
void *cb UNUSED)
{
if (!strcmp(var, "diff.indentheuristic"))
diff_indent_heuristic = git_config_bool(var, value);
return 0;
}
static int parse_color_moved(const char *arg)
{
switch (git_parse_maybe_bool(arg)) {
case 0:
return COLOR_MOVED_NO;
case 1:
return COLOR_MOVED_DEFAULT;
default:
break;
}
if (!strcmp(arg, "no"))
return COLOR_MOVED_NO;
else if (!strcmp(arg, "plain"))
return COLOR_MOVED_PLAIN;
else if (!strcmp(arg, "blocks"))
return COLOR_MOVED_BLOCKS;
else if (!strcmp(arg, "zebra"))
return COLOR_MOVED_ZEBRA;
else if (!strcmp(arg, "default"))
return COLOR_MOVED_DEFAULT;
else if (!strcmp(arg, "dimmed-zebra"))
return COLOR_MOVED_ZEBRA_DIM;
else if (!strcmp(arg, "dimmed_zebra"))
return COLOR_MOVED_ZEBRA_DIM;
else
return error(_("color moved setting must be one of 'no', 'default', 'blocks', 'zebra', 'dimmed-zebra', 'plain'"));
}
static unsigned parse_color_moved_ws(const char *arg)
{
int ret = 0;
struct string_list l = STRING_LIST_INIT_DUP;
struct string_list_item *i;
string_list_split(&l, arg, ',', -1);
for_each_string_list_item(i, &l) {
struct strbuf sb = STRBUF_INIT;
strbuf_addstr(&sb, i->string);
strbuf_trim(&sb);
if (!strcmp(sb.buf, "no"))
ret = 0;
else if (!strcmp(sb.buf, "ignore-space-change"))
ret |= XDF_IGNORE_WHITESPACE_CHANGE;
else if (!strcmp(sb.buf, "ignore-space-at-eol"))
ret |= XDF_IGNORE_WHITESPACE_AT_EOL;
else if (!strcmp(sb.buf, "ignore-all-space"))
ret |= XDF_IGNORE_WHITESPACE;
else if (!strcmp(sb.buf, "allow-indentation-change"))
ret |= COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE;
else {
ret |= COLOR_MOVED_WS_ERROR;
error(_("unknown color-moved-ws mode '%s', possible values are 'ignore-space-change', 'ignore-space-at-eol', 'ignore-all-space', 'allow-indentation-change'"), sb.buf);
}
strbuf_release(&sb);
}
if ((ret & COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE) &&
(ret & XDF_WHITESPACE_FLAGS)) {
error(_("color-moved-ws: allow-indentation-change cannot be combined with other whitespace modes"));
ret |= COLOR_MOVED_WS_ERROR;
}
string_list_clear(&l, 0);
return ret;
}
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);
return 0;
}
if (!strcmp(var, "diff.colormoved")) {
int cm = parse_color_moved(value);
if (cm < 0)
return -1;
diff_color_moved_default = cm;
return 0;
}
if (!strcmp(var, "diff.colormovedws")) {
unsigned cm = parse_color_moved_ws(value);
if (cm & COLOR_MOVED_WS_ERROR)
return -1;
diff_color_moved_ws_default = cm;
return 0;
}
if (!strcmp(var, "diff.context")) {
diff_context_default = git_config_int(var, value);
if (diff_context_default < 0)
return -1;
return 0;
}
if (!strcmp(var, "diff.interhunkcontext")) {
diff_interhunk_context_default = git_config_int(var, value);
if (diff_interhunk_context_default < 0)
return -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.noprefix")) {
diff_no_prefix = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "diff.relative")) {
diff_relative = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "diff.statgraphwidth")) {
diff_stat_graph_width = git_config_int(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);
if (!strcmp(var, "diff.orderfile"))
return git_config_pathname(&diff_order_file_cfg, var, value);
if (!strcmp(var, "diff.ignoresubmodules"))
handle_ignore_submodules_arg(&default_diff_options, value);
if (!strcmp(var, "diff.submodule")) {
if (parse_submodule_params(&default_diff_options, value))
warning(_("Unknown value for 'diff.submodule' config variable: '%s'"),
value);
return 0;
}
if (!strcmp(var, "diff.algorithm")) {
diff_algorithm = parse_algorithm_value(value);
if (diff_algorithm < 0)
return -1;
return 0;
}
if (git_color_config(var, value, cb) < 0)
return -1;
return git_diff_basic_config(var, value, cb);
}
int git_diff_basic_config(const char *var, const char *value, void *cb)
{
const char *name;
if (!strcmp(var, "diff.renamelimit")) {
diff_rename_limit_default = git_config_int(var, value);
return 0;
}
if (userdiff_config(var, value) < 0)
return -1;
if (skip_prefix(var, "diff.color.", &name) ||
skip_prefix(var, "color.diff.", &name)) {
int slot = parse_diff_color_slot(name);
if (slot < 0)
return 0;
if (!value)
return config_error_nonbool(var);
return color_parse(value, diff_colors[slot]);
}
if (!strcmp(var, "diff.wserrorhighlight")) {
int val = parse_ws_error_highlight(value);
if (val < 0)
return -1;
ws_error_highlight_default = val;
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;
}
if (!strcmp(var, "diff.dirstat")) {
struct strbuf errmsg = STRBUF_INIT;
default_diff_options.dirstat_permille = diff_dirstat_permille_default;
if (parse_dirstat_params(&default_diff_options, value, &errmsg))
warning(_("Found errors in 'diff.dirstat' config variable:\n%s"),
errmsg.buf);
strbuf_release(&errmsg);
diff_dirstat_permille_default = default_diff_options.dirstat_permille;
return 0;
}
if (git_diff_heuristic_config(var, value, cb) < 0)
return -1;
return git_default_config(var, value, cb);
}
static char *quote_two(const char *one, const char *two)
{
int need_one = quote_c_style(one, NULL, NULL, CQUOTE_NODQ);
int need_two = quote_c_style(two, NULL, NULL, CQUOTE_NODQ);
struct strbuf res = STRBUF_INIT;
if (need_one + need_two) {
strbuf_addch(&res, '"');
quote_c_style(one, &res, NULL, CQUOTE_NODQ);
quote_c_style(two, &res, NULL, CQUOTE_NODQ);
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 = xstrdup_or_null(getenv("GIT_EXTERNAL_DIFF"));
if (!external_diff_cmd)
external_diff_cmd = external_diff_cmd_cfg;
done_preparing = 1;
return external_diff_cmd;
}
/*
* Keep track of files used for diffing. Sometimes such an entry
* refers to a temporary file, sometimes to an existing file, and
* sometimes to "/dev/null".
*/
static struct diff_tempfile {
/*
* filename external diff should read from, or NULL if this
* entry is currently not in use:
*/
const char *name;
char hex[GIT_MAX_HEXSZ + 1];
char mode[10];
/*
* If this diff_tempfile instance refers to a temporary file,
* this tempfile object is used to manage its lifetime.
*/
struct tempfile *tempfile;
} diff_temp[2];
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;
const char **label_path;
struct diff_words_data *diff_words;
struct diff_options *opt;
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(struct repository *r, 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(r, one, NULL))
return -1;
mf->ptr = one->data;
mf->size = one->size;
return 0;
}
/* like fill_mmfile, but only for size, so we can avoid retrieving blob */
static unsigned long diff_filespec_size(struct repository *r,
struct diff_filespec *one)
{
struct diff_populate_filespec_options dpf_options = {
.check_size_only = 1,
};
if (!DIFF_FILE_VALID(one))
return 0;
diff_populate_filespec(r, one, &dpf_options);
return one->size;
}
static int count_trailing_blank(mmfile_t *mf)
{
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))
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;
l1 = count_trailing_blank(mf1);
l2 = count_trailing_blank(mf2);
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(struct diff_options *o,
const char *set_sign, const char *set, unsigned reverse, const char *reset,
int first, const char *line, int len)
{
int has_trailing_newline, has_trailing_carriage_return;
int needs_reset = 0; /* at the end of the line */
FILE *file = o->file;
fputs(diff_line_prefix(o), file);
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--;
if (!len && !first)
goto end_of_line;
if (reverse && want_color(o->use_color)) {
fputs(GIT_COLOR_REVERSE, file);
needs_reset = 1;
}
if (set_sign) {
fputs(set_sign, file);
needs_reset = 1;
}
if (first)
fputc(first, file);
if (!len)
goto end_of_line;
if (set) {
if (set_sign && set != set_sign)
fputs(reset, file);
fputs(set, file);
needs_reset = 1;
}
fwrite(line, len, 1, file);
needs_reset = 1; /* 'line' may contain color codes. */
end_of_line:
if (needs_reset)
fputs(reset, file);
if (has_trailing_carriage_return)
fputc('\r', file);
if (has_trailing_newline)
fputc('\n', file);
}
static void emit_line(struct diff_options *o, const char *set, const char *reset,
const char *line, int len)
{
emit_line_0(o, set, NULL, 0, reset, 0, line, len);
}
enum diff_symbol {
DIFF_SYMBOL_BINARY_DIFF_HEADER,
DIFF_SYMBOL_BINARY_DIFF_HEADER_DELTA,
DIFF_SYMBOL_BINARY_DIFF_HEADER_LITERAL,
DIFF_SYMBOL_BINARY_DIFF_BODY,
DIFF_SYMBOL_BINARY_DIFF_FOOTER,
DIFF_SYMBOL_STATS_SUMMARY_NO_FILES,
DIFF_SYMBOL_STATS_SUMMARY_ABBREV,
DIFF_SYMBOL_STATS_SUMMARY_INSERTS_DELETES,
DIFF_SYMBOL_STATS_LINE,
DIFF_SYMBOL_WORD_DIFF,
DIFF_SYMBOL_STAT_SEP,
DIFF_SYMBOL_SUMMARY,
DIFF_SYMBOL_SUBMODULE_ADD,
DIFF_SYMBOL_SUBMODULE_DEL,
DIFF_SYMBOL_SUBMODULE_UNTRACKED,
DIFF_SYMBOL_SUBMODULE_MODIFIED,
DIFF_SYMBOL_SUBMODULE_HEADER,
DIFF_SYMBOL_SUBMODULE_ERROR,
DIFF_SYMBOL_SUBMODULE_PIPETHROUGH,
DIFF_SYMBOL_REWRITE_DIFF,
DIFF_SYMBOL_BINARY_FILES,
DIFF_SYMBOL_HEADER,
DIFF_SYMBOL_FILEPAIR_PLUS,
DIFF_SYMBOL_FILEPAIR_MINUS,
DIFF_SYMBOL_WORDS_PORCELAIN,
DIFF_SYMBOL_WORDS,
DIFF_SYMBOL_CONTEXT,
DIFF_SYMBOL_CONTEXT_INCOMPLETE,
DIFF_SYMBOL_PLUS,
DIFF_SYMBOL_MINUS,
DIFF_SYMBOL_NO_LF_EOF,
DIFF_SYMBOL_CONTEXT_FRAGINFO,
DIFF_SYMBOL_CONTEXT_MARKER,
DIFF_SYMBOL_SEPARATOR
};
/*
* Flags for content lines:
* 0..12 are whitespace rules
* 13-15 are WSEH_NEW | WSEH_OLD | WSEH_CONTEXT
* 16 is marking if the line is blank at EOF
*/
#define DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF (1<<16)
#define DIFF_SYMBOL_MOVED_LINE (1<<17)
#define DIFF_SYMBOL_MOVED_LINE_ALT (1<<18)
#define DIFF_SYMBOL_MOVED_LINE_UNINTERESTING (1<<19)
#define DIFF_SYMBOL_CONTENT_WS_MASK (WSEH_NEW | WSEH_OLD | WSEH_CONTEXT | WS_RULE_MASK)
/*
* This struct is used when we need to buffer the output of the diff output.
*
* NEEDSWORK: Instead of storing a copy of the line, add an offset pointer
* into the pre/post image file. This pointer could be a union with the
* line pointer. By storing an offset into the file instead of the literal line,
* we can decrease the memory footprint for the buffered output. At first we
* may want to only have indirection for the content lines, but we could also
* enhance the state for emitting prefabricated lines, e.g. the similarity
* score line or hunk/file headers would only need to store a number or path
* and then the output can be constructed later on depending on state.
*/
struct emitted_diff_symbol {
const char *line;
int len;
int flags;
int indent_off; /* Offset to first non-whitespace character */
int indent_width; /* The visual width of the indentation */
unsigned id;
enum diff_symbol s;
};
#define EMITTED_DIFF_SYMBOL_INIT { 0 }
struct emitted_diff_symbols {
struct emitted_diff_symbol *buf;
int nr, alloc;
};
#define EMITTED_DIFF_SYMBOLS_INIT { 0 }
static void append_emitted_diff_symbol(struct diff_options *o,
struct emitted_diff_symbol *e)
{
struct emitted_diff_symbol *f;
ALLOC_GROW(o->emitted_symbols->buf,
o->emitted_symbols->nr + 1,
o->emitted_symbols->alloc);
f = &o->emitted_symbols->buf[o->emitted_symbols->nr++];
memcpy(f, e, sizeof(struct emitted_diff_symbol));
f->line = e->line ? xmemdupz(e->line, e->len) : NULL;
}
static void free_emitted_diff_symbols(struct emitted_diff_symbols *e)
{
if (!e)
return;
free(e->buf);
free(e);
}
struct moved_entry {
const struct emitted_diff_symbol *es;
struct moved_entry *next_line;
struct moved_entry *next_match;
};
struct moved_block {
struct moved_entry *match;
int wsd; /* The whitespace delta of this block */
};
#define INDENT_BLANKLINE INT_MIN
static void fill_es_indent_data(struct emitted_diff_symbol *es)
{
unsigned int off = 0, i;
int width = 0, tab_width = es->flags & WS_TAB_WIDTH_MASK;
const char *s = es->line;
const int len = es->len;
/* skip any \v \f \r at start of indentation */
while (s[off] == '\f' || s[off] == '\v' ||
(s[off] == '\r' && off < len - 1))
off++;
/* calculate the visual width of indentation */
while(1) {
if (s[off] == ' ') {
width++;
off++;
} else if (s[off] == '\t') {
width += tab_width - (width % tab_width);
while (s[++off] == '\t')
width += tab_width;
} else {
break;
}
}
/* check if this line is blank */
for (i = off; i < len; i++)
if (!isspace(s[i]))
break;
if (i == len) {
es->indent_width = INDENT_BLANKLINE;
es->indent_off = len;
} else {
es->indent_off = off;
es->indent_width = width;
}
}
static int compute_ws_delta(const struct emitted_diff_symbol *a,
const struct emitted_diff_symbol *b)
{
int a_width = a->indent_width,
b_width = b->indent_width;
if (a_width == INDENT_BLANKLINE && b_width == INDENT_BLANKLINE)
return INDENT_BLANKLINE;
return a_width - b_width;
}
static int cmp_in_block_with_wsd(const struct moved_entry *cur,
const struct emitted_diff_symbol *l,
struct moved_block *pmb)
{
int a_width = cur->es->indent_width, b_width = l->indent_width;
int delta;
/* The text of each line must match */
if (cur->es->id != l->id)
return 1;
/*
* If 'l' and 'cur' are both blank then we don't need to check the
* indent. We only need to check cur as we know the strings match.
* */
if (a_width == INDENT_BLANKLINE)
return 0;
/*
* The indent changes of the block are known and stored in pmb->wsd;
* however we need to check if the indent changes of the current line
* match those of the current block.
*/
delta = b_width - a_width;
/*
* If the previous lines of this block were all blank then set its
* whitespace delta.
*/
if (pmb->wsd == INDENT_BLANKLINE)
pmb->wsd = delta;
return delta != pmb->wsd;
}
struct interned_diff_symbol {
struct hashmap_entry ent;
struct emitted_diff_symbol *es;
};
static int interned_diff_symbol_cmp(const void *hashmap_cmp_fn_data,
const struct hashmap_entry *eptr,
const struct hashmap_entry *entry_or_key,
const void *keydata UNUSED)
{
const struct diff_options *diffopt = hashmap_cmp_fn_data;
const struct emitted_diff_symbol *a, *b;
unsigned flags = diffopt->color_moved_ws_handling
& XDF_WHITESPACE_FLAGS;
a = container_of(eptr, const struct interned_diff_symbol, ent)->es;
b = container_of(entry_or_key, const struct interned_diff_symbol, ent)->es;
return !xdiff_compare_lines(a->line + a->indent_off,
a->len - a->indent_off,
b->line + b->indent_off,
b->len - b->indent_off, flags);
}
static void prepare_entry(struct diff_options *o, struct emitted_diff_symbol *l,
struct interned_diff_symbol *s)
{
unsigned flags = o->color_moved_ws_handling & XDF_WHITESPACE_FLAGS;
unsigned int hash = xdiff_hash_string(l->line + l->indent_off,
l->len - l->indent_off, flags);
hashmap_entry_init(&s->ent, hash);
s->es = l;
}
struct moved_entry_list {
struct moved_entry *add, *del;
};
static struct moved_entry_list *add_lines_to_move_detection(struct diff_options *o,
struct mem_pool *entry_mem_pool)
{
struct moved_entry *prev_line = NULL;
struct mem_pool interned_pool;
struct hashmap interned_map;
struct moved_entry_list *entry_list = NULL;
size_t entry_list_alloc = 0;
unsigned id = 0;
int n;
hashmap_init(&interned_map, interned_diff_symbol_cmp, o, 8096);
mem_pool_init(&interned_pool, 1024 * 1024);
for (n = 0; n < o->emitted_symbols->nr; n++) {
struct interned_diff_symbol key;
struct emitted_diff_symbol *l = &o->emitted_symbols->buf[n];
struct interned_diff_symbol *s;
struct moved_entry *entry;
if (l->s != DIFF_SYMBOL_PLUS && l->s != DIFF_SYMBOL_MINUS) {
prev_line = NULL;
continue;
}
if (o->color_moved_ws_handling &
COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE)
fill_es_indent_data(l);
prepare_entry(o, l, &key);
s = hashmap_get_entry(&interned_map, &key, ent, &key.ent);
if (s) {
l->id = s->es->id;
} else {
l->id = id;
ALLOC_GROW_BY(entry_list, id, 1, entry_list_alloc);
hashmap_add(&interned_map,
memcpy(mem_pool_alloc(&interned_pool,
sizeof(key)),
&key, sizeof(key)));
}
entry = mem_pool_alloc(entry_mem_pool, sizeof(*entry));
entry->es = l;
entry->next_line = NULL;
if (prev_line && prev_line->es->s == l->s)
prev_line->next_line = entry;
prev_line = entry;
if (l->s == DIFF_SYMBOL_PLUS) {
entry->next_match = entry_list[l->id].add;
entry_list[l->id].add = entry;
} else {
entry->next_match = entry_list[l->id].del;
entry_list[l->id].del = entry;
}
}
hashmap_clear(&interned_map);
mem_pool_discard(&interned_pool, 0);
return entry_list;
}
static void pmb_advance_or_null(struct diff_options *o,
struct emitted_diff_symbol *l,
struct moved_block *pmb,
int *pmb_nr)
{
int i, j;
for (i = 0, j = 0; i < *pmb_nr; i++) {
int match;
struct moved_entry *prev = pmb[i].match;
struct moved_entry *cur = (prev && prev->next_line) ?
prev->next_line : NULL;
if (o->color_moved_ws_handling &
COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE)
match = cur &&
!cmp_in_block_with_wsd(cur, l, &pmb[i]);
else
match = cur && cur->es->id == l->id;
if (match) {
pmb[j] = pmb[i];
pmb[j++].match = cur;
}
}
*pmb_nr = j;
}
static void fill_potential_moved_blocks(struct diff_options *o,
struct moved_entry *match,
struct emitted_diff_symbol *l,
struct moved_block **pmb_p,
int *pmb_alloc_p, int *pmb_nr_p)
{
struct moved_block *pmb = *pmb_p;
int pmb_alloc = *pmb_alloc_p, pmb_nr = *pmb_nr_p;
/*
* The current line is the start of a new block.
* Setup the set of potential blocks.
*/
for (; match; match = match->next_match) {
ALLOC_GROW(pmb, pmb_nr + 1, pmb_alloc);
if (o->color_moved_ws_handling &
COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE)
pmb[pmb_nr].wsd = compute_ws_delta(l, match->es);
else
pmb[pmb_nr].wsd = 0;
pmb[pmb_nr++].match = match;
}
*pmb_p = pmb;
*pmb_alloc_p = pmb_alloc;
*pmb_nr_p = pmb_nr;
}
/*
* If o->color_moved is COLOR_MOVED_PLAIN, this function does nothing.
*
* Otherwise, if the last block has fewer alphanumeric characters than
* COLOR_MOVED_MIN_ALNUM_COUNT, unset DIFF_SYMBOL_MOVED_LINE on all lines in
* that block.
*
* The last block consists of the (n - block_length)'th line up to but not
* including the nth line.
*
* Returns 0 if the last block is empty or is unset by this function, non zero
* otherwise.
*
* NEEDSWORK: This uses the same heuristic as blame_entry_score() in blame.c.
* Think of a way to unify them.
*/
#define DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK \
(DIFF_SYMBOL_MOVED_LINE | DIFF_SYMBOL_MOVED_LINE_ALT)
static int adjust_last_block(struct diff_options *o, int n, int block_length)
{
int i, alnum_count = 0;
if (o->color_moved == COLOR_MOVED_PLAIN)
return block_length;
for (i = 1; i < block_length + 1; i++) {
const char *c = o->emitted_symbols->buf[n - i].line;
for (; *c; c++) {
if (!isalnum(*c))
continue;
alnum_count++;
if (alnum_count >= COLOR_MOVED_MIN_ALNUM_COUNT)
return 1;
}
}
for (i = 1; i < block_length + 1; i++)
o->emitted_symbols->buf[n - i].flags &= ~DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK;
return 0;
}
/* Find blocks of moved code, delegate actual coloring decision to helper */
static void mark_color_as_moved(struct diff_options *o,
struct moved_entry_list *entry_list)
{
struct moved_block *pmb = NULL; /* potentially moved blocks */
int pmb_nr = 0, pmb_alloc = 0;
int n, flipped_block = 0, block_length = 0;
enum diff_symbol moved_symbol = DIFF_SYMBOL_BINARY_DIFF_HEADER;
for (n = 0; n < o->emitted_symbols->nr; n++) {
struct moved_entry *match = NULL;
struct emitted_diff_symbol *l = &o->emitted_symbols->buf[n];
switch (l->s) {
case DIFF_SYMBOL_PLUS:
match = entry_list[l->id].del;
break;
case DIFF_SYMBOL_MINUS:
match = entry_list[l->id].add;
break;
default:
flipped_block = 0;
}
if (pmb_nr && (!match || l->s != moved_symbol)) {
if (!adjust_last_block(o, n, block_length) &&
block_length > 1) {
/*
* Rewind in case there is another match
* starting at the second line of the block
*/
match = NULL;
n -= block_length;
}
pmb_nr = 0;
block_length = 0;
flipped_block = 0;
}
if (!match) {
moved_symbol = DIFF_SYMBOL_BINARY_DIFF_HEADER;
continue;
}
if (o->color_moved == COLOR_MOVED_PLAIN) {
l->flags |= DIFF_SYMBOL_MOVED_LINE;
continue;
}
pmb_advance_or_null(o, l, pmb, &pmb_nr);
if (pmb_nr == 0) {
int contiguous = adjust_last_block(o, n, block_length);
if (!contiguous && block_length > 1)
/*
* Rewind in case there is another match
* starting at the second line of the block
*/
n -= block_length;
else
fill_potential_moved_blocks(o, match, l,
&pmb, &pmb_alloc,
&pmb_nr);
if (contiguous && pmb_nr && moved_symbol == l->s)
flipped_block = (flipped_block + 1) % 2;
else
flipped_block = 0;
if (pmb_nr)
moved_symbol = l->s;
else
moved_symbol = DIFF_SYMBOL_BINARY_DIFF_HEADER;
block_length = 0;
}
if (pmb_nr) {
block_length++;
l->flags |= DIFF_SYMBOL_MOVED_LINE;
if (flipped_block && o->color_moved != COLOR_MOVED_BLOCKS)
l->flags |= DIFF_SYMBOL_MOVED_LINE_ALT;
}
}
adjust_last_block(o, n, block_length);
free(pmb);
}
static void dim_moved_lines(struct diff_options *o)
{
int n;
for (n = 0; n < o->emitted_symbols->nr; n++) {
struct emitted_diff_symbol *prev = (n != 0) ?
&o->emitted_symbols->buf[n - 1] : NULL;
struct emitted_diff_symbol *l = &o->emitted_symbols->buf[n];
struct emitted_diff_symbol *next =
(n < o->emitted_symbols->nr - 1) ?
&o->emitted_symbols->buf[n + 1] : NULL;
/* Not a plus or minus line? */
if (l->s != DIFF_SYMBOL_PLUS && l->s != DIFF_SYMBOL_MINUS)
continue;
/* Not a moved line? */
if (!(l->flags & DIFF_SYMBOL_MOVED_LINE))
continue;
/*
* If prev or next are not a plus or minus line,
* pretend they don't exist
*/
if (prev && prev->s != DIFF_SYMBOL_PLUS &&
prev->s != DIFF_SYMBOL_MINUS)
prev = NULL;
if (next && next->s != DIFF_SYMBOL_PLUS &&
next->s != DIFF_SYMBOL_MINUS)
next = NULL;
/* Inside a block? */
if ((prev &&
(prev->flags & DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK) ==
(l->flags & DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK)) &&
(next &&
(next->flags & DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK) ==
(l->flags & DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK))) {
l->flags |= DIFF_SYMBOL_MOVED_LINE_UNINTERESTING;
continue;
}
/* Check if we are at an interesting bound: */
if (prev && (prev->flags & DIFF_SYMBOL_MOVED_LINE) &&
(prev->flags & DIFF_SYMBOL_MOVED_LINE_ALT) !=
(l->flags & DIFF_SYMBOL_MOVED_LINE_ALT))
continue;
if (next && (next->flags & DIFF_SYMBOL_MOVED_LINE) &&
(next->flags & DIFF_SYMBOL_MOVED_LINE_ALT) !=
(l->flags & DIFF_SYMBOL_MOVED_LINE_ALT))
continue;
/*
* The boundary to prev and next are not interesting,
* so this line is not interesting as a whole
*/
l->flags |= DIFF_SYMBOL_MOVED_LINE_UNINTERESTING;
}
}
static void emit_line_ws_markup(struct diff_options *o,
const char *set_sign, const char *set,
const char *reset,
int sign_index, const char *line, int len,
unsigned ws_rule, int blank_at_eof)
{
const char *ws = NULL;
int sign = o->output_indicators[sign_index];
if (o->ws_error_highlight & ws_rule) {
ws = diff_get_color_opt(o, DIFF_WHITESPACE);
if (!*ws)
ws = NULL;
}
if (!ws && !set_sign)
emit_line_0(o, set, NULL, 0, reset, sign, line, len);
else if (!ws) {
emit_line_0(o, set_sign, set, !!set_sign, reset, sign, line, len);
} else if (blank_at_eof)
/* Blank line at EOF - paint '+' as well */
emit_line_0(o, ws, NULL, 0, reset, sign, line, len);
else {
/* Emit just the prefix, then the rest. */
emit_line_0(o, set_sign ? set_sign : set, NULL, !!set_sign, reset,
sign, "", 0);
ws_check_emit(line, len, ws_rule,
o->file, set, reset, ws);
}
}
static void emit_diff_symbol_from_struct(struct diff_options *o,
struct emitted_diff_symbol *eds)
{
static const char *nneof = " No newline at end of file\n";
const char *context, *reset, *set, *set_sign, *meta, *fraginfo;
enum diff_symbol s = eds->s;
const char *line = eds->line;
int len = eds->len;
unsigned flags = eds->flags;
switch (s) {
case DIFF_SYMBOL_NO_LF_EOF:
context = diff_get_color_opt(o, DIFF_CONTEXT);
reset = diff_get_color_opt(o, DIFF_RESET);
putc('\n', o->file);
emit_line_0(o, context, NULL, 0, reset, '\\',
nneof, strlen(nneof));
break;
case DIFF_SYMBOL_SUBMODULE_HEADER:
case DIFF_SYMBOL_SUBMODULE_ERROR:
case DIFF_SYMBOL_SUBMODULE_PIPETHROUGH:
case DIFF_SYMBOL_STATS_SUMMARY_INSERTS_DELETES:
case DIFF_SYMBOL_SUMMARY:
case DIFF_SYMBOL_STATS_LINE:
case DIFF_SYMBOL_BINARY_DIFF_BODY:
case DIFF_SYMBOL_CONTEXT_FRAGINFO:
emit_line(o, "", "", line, len);
break;
case DIFF_SYMBOL_CONTEXT_INCOMPLETE:
case DIFF_SYMBOL_CONTEXT_MARKER:
context = diff_get_color_opt(o, DIFF_CONTEXT);
reset = diff_get_color_opt(o, DIFF_RESET);
emit_line(o, context, reset, line, len);
break;
case DIFF_SYMBOL_SEPARATOR:
fprintf(o->file, "%s%c",
diff_line_prefix(o),
o->line_termination);
break;
case DIFF_SYMBOL_CONTEXT:
set = diff_get_color_opt(o, DIFF_CONTEXT);
reset = diff_get_color_opt(o, DIFF_RESET);
set_sign = NULL;
if (o->flags.dual_color_diffed_diffs) {
char c = !len ? 0 : line[0];
if (c == '+')
set = diff_get_color_opt(o, DIFF_FILE_NEW);
else if (c == '@')
set = diff_get_color_opt(o, DIFF_FRAGINFO);
else if (c == '-')
set = diff_get_color_opt(o, DIFF_FILE_OLD);
}
emit_line_ws_markup(o, set_sign, set, reset,
OUTPUT_INDICATOR_CONTEXT, line, len,
flags & (DIFF_SYMBOL_CONTENT_WS_MASK), 0);
break;
case DIFF_SYMBOL_PLUS:
switch (flags & (DIFF_SYMBOL_MOVED_LINE |
DIFF_SYMBOL_MOVED_LINE_ALT |
DIFF_SYMBOL_MOVED_LINE_UNINTERESTING)) {
case DIFF_SYMBOL_MOVED_LINE |
DIFF_SYMBOL_MOVED_LINE_ALT |
DIFF_SYMBOL_MOVED_LINE_UNINTERESTING:
set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED_ALT_DIM);
break;
case DIFF_SYMBOL_MOVED_LINE |
DIFF_SYMBOL_MOVED_LINE_ALT:
set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED_ALT);
break;
case DIFF_SYMBOL_MOVED_LINE |
DIFF_SYMBOL_MOVED_LINE_UNINTERESTING:
set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED_DIM);
break;
case DIFF_SYMBOL_MOVED_LINE:
set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED);
break;
default:
set = diff_get_color_opt(o, DIFF_FILE_NEW);
}
reset = diff_get_color_opt(o, DIFF_RESET);
if (!o->flags.dual_color_diffed_diffs)
set_sign = NULL;
else {
char c = !len ? 0 : line[0];
set_sign = set;
if (c == '-')
set = diff_get_color_opt(o, DIFF_FILE_OLD_BOLD);
else if (c == '@')
set = diff_get_color_opt(o, DIFF_FRAGINFO);
else if (c == '+')
set = diff_get_color_opt(o, DIFF_FILE_NEW_BOLD);
else
set = diff_get_color_opt(o, DIFF_CONTEXT_BOLD);
flags &= ~DIFF_SYMBOL_CONTENT_WS_MASK;
}
emit_line_ws_markup(o, set_sign, set, reset,
OUTPUT_INDICATOR_NEW, line, len,
flags & DIFF_SYMBOL_CONTENT_WS_MASK,
flags & DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF);
break;
case DIFF_SYMBOL_MINUS:
switch (flags & (DIFF_SYMBOL_MOVED_LINE |
DIFF_SYMBOL_MOVED_LINE_ALT |
DIFF_SYMBOL_MOVED_LINE_UNINTERESTING)) {
case DIFF_SYMBOL_MOVED_LINE |
DIFF_SYMBOL_MOVED_LINE_ALT |
DIFF_SYMBOL_MOVED_LINE_UNINTERESTING:
set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED_ALT_DIM);
break;
case DIFF_SYMBOL_MOVED_LINE |
DIFF_SYMBOL_MOVED_LINE_ALT:
set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED_ALT);
break;
case DIFF_SYMBOL_MOVED_LINE |
DIFF_SYMBOL_MOVED_LINE_UNINTERESTING:
set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED_DIM);
break;
case DIFF_SYMBOL_MOVED_LINE:
set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED);
break;
default:
set = diff_get_color_opt(o, DIFF_FILE_OLD);
}
reset = diff_get_color_opt(o, DIFF_RESET);
if (!o->flags.dual_color_diffed_diffs)
set_sign = NULL;
else {
char c = !len ? 0 : line[0];
set_sign = set;
if (c == '+')
set = diff_get_color_opt(o, DIFF_FILE_NEW_DIM);
else if (c == '@')
set = diff_get_color_opt(o, DIFF_FRAGINFO);
else if (c == '-')
set = diff_get_color_opt(o, DIFF_FILE_OLD_DIM);
else
set = diff_get_color_opt(o, DIFF_CONTEXT_DIM);
}
emit_line_ws_markup(o, set_sign, set, reset,
OUTPUT_INDICATOR_OLD, line, len,
flags & DIFF_SYMBOL_CONTENT_WS_MASK, 0);
break;
case DIFF_SYMBOL_WORDS_PORCELAIN:
context = diff_get_color_opt(o, DIFF_CONTEXT);
reset = diff_get_color_opt(o, DIFF_RESET);
emit_line(o, context, reset, line, len);
fputs("~\n", o->file);
break;
case DIFF_SYMBOL_WORDS:
context = diff_get_color_opt(o, DIFF_CONTEXT);
reset = diff_get_color_opt(o, DIFF_RESET);
/*
* Skip the prefix character, if any. With
* diff_suppress_blank_empty, there may be
* none.
*/
if (line[0] != '\n') {
line++;
len--;
}
emit_line(o, context, reset, line, len);
break;
case DIFF_SYMBOL_FILEPAIR_PLUS:
meta = diff_get_color_opt(o, DIFF_METAINFO);
reset = diff_get_color_opt(o, DIFF_RESET);
fprintf(o->file, "%s%s+++ %s%s%s\n", diff_line_prefix(o), meta,
line, reset,
strchr(line, ' ') ? "\t" : "");
break;
case DIFF_SYMBOL_FILEPAIR_MINUS:
meta = diff_get_color_opt(o, DIFF_METAINFO);
reset = diff_get_color_opt(o, DIFF_RESET);
fprintf(o->file, "%s%s--- %s%s%s\n", diff_line_prefix(o), meta,
line, reset,
strchr(line, ' ') ? "\t" : "");
break;
case DIFF_SYMBOL_BINARY_FILES:
case DIFF_SYMBOL_HEADER:
fprintf(o->file, "%s", line);
break;
case DIFF_SYMBOL_BINARY_DIFF_HEADER:
fprintf(o->file, "%sGIT binary patch\n", diff_line_prefix(o));
break;
case DIFF_SYMBOL_BINARY_DIFF_HEADER_DELTA:
fprintf(o->file, "%sdelta %s\n", diff_line_prefix(o), line);
break;
case DIFF_SYMBOL_BINARY_DIFF_HEADER_LITERAL:
fprintf(o->file, "%sliteral %s\n", diff_line_prefix(o), line);
break;
case DIFF_SYMBOL_BINARY_DIFF_FOOTER:
fputs(diff_line_prefix(o), o->file);
fputc('\n', o->file);
break;
case DIFF_SYMBOL_REWRITE_DIFF:
fraginfo = diff_get_color(o->use_color, DIFF_FRAGINFO);
reset = diff_get_color_opt(o, DIFF_RESET);
emit_line(o, fraginfo, reset, line, len);
break;
case DIFF_SYMBOL_SUBMODULE_ADD:
set = diff_get_color_opt(o, DIFF_FILE_NEW);
reset = diff_get_color_opt(o, DIFF_RESET);
emit_line(o, set, reset, line, len);
break;
case DIFF_SYMBOL_SUBMODULE_DEL:
set = diff_get_color_opt(o, DIFF_FILE_OLD);
reset = diff_get_color_opt(o, DIFF_RESET);
emit_line(o, set, reset, line, len);
break;
case DIFF_SYMBOL_SUBMODULE_UNTRACKED:
fprintf(o->file, "%sSubmodule %s contains untracked content\n",
diff_line_prefix(o), line);
break;
case DIFF_SYMBOL_SUBMODULE_MODIFIED:
fprintf(o->file, "%sSubmodule %s contains modified content\n",
diff_line_prefix(o), line);
break;
case DIFF_SYMBOL_STATS_SUMMARY_NO_FILES:
emit_line(o, "", "", " 0 files changed\n",
strlen(" 0 files changed\n"));
break;
case DIFF_SYMBOL_STATS_SUMMARY_ABBREV:
emit_line(o, "", "", " ...\n", strlen(" ...\n"));
break;
case DIFF_SYMBOL_WORD_DIFF:
fprintf(o->file, "%.*s", len, line);
break;
case DIFF_SYMBOL_STAT_SEP:
fputs(o->stat_sep, o->file);
break;
default:
BUG("unknown diff symbol");
}
}
static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
const char *line, int len, unsigned flags)
{
struct emitted_diff_symbol e = {
.line = line, .len = len, .flags = flags, .s = s
};
if (o->emitted_symbols)
append_emitted_diff_symbol(o, &e);
else
emit_diff_symbol_from_struct(o, &e);
}
void diff_emit_submodule_del(struct diff_options *o, const char *line)
{
emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_DEL, line, strlen(line), 0);
}
void diff_emit_submodule_add(struct diff_options *o, const char *line)
{
emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_ADD, line, strlen(line), 0);
}
void diff_emit_submodule_untracked(struct diff_options *o, const char *path)
{
emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_UNTRACKED,
path, strlen(path), 0);
}
void diff_emit_submodule_modified(struct diff_options *o, const char *path)
{
emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_MODIFIED,
path, strlen(path), 0);
}
void diff_emit_submodule_header(struct diff_options *o, const char *header)
{
emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_HEADER,
header, strlen(header), 0);
}
void diff_emit_submodule_error(struct diff_options *o, const char *err)
{
emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_ERROR, err, strlen(err), 0);
}
void diff_emit_submodule_pipethrough(struct diff_options *o,
const char *line, int len)
{
emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_PIPETHROUGH, line, len, 0);
}
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);
}
static void emit_add_line(struct emit_callback *ecbdata,
const char *line, int len)
{
unsigned flags = WSEH_NEW | ecbdata->ws_rule;
if (new_blank_line_at_eof(ecbdata, line, len))
flags |= DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF;
emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_PLUS, line, len, flags);
}
static void emit_del_line(struct emit_callback *ecbdata,
const char *line, int len)
{
unsigned flags = WSEH_OLD | ecbdata->ws_rule;
emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_MINUS, line, len, flags);
}
static void emit_context_line(struct emit_callback *ecbdata,
const char *line, int len)
{
unsigned flags = WSEH_CONTEXT | ecbdata->ws_rule;
emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_CONTEXT, line, len, flags);
}
static void emit_hunk_header(struct emit_callback *ecbdata,
const char *line, int len)
{
const char *context = diff_get_color(ecbdata->color_diff, DIFF_CONTEXT);
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);
const char *reverse = ecbdata->color_diff ? GIT_COLOR_REVERSE : "";
static const char atat[2] = { '@', '@' };
const char *cp, *ep;
struct strbuf msgbuf = STRBUF_INIT;
int org_len = len;
int i = 1;
/*
* 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_diff_symbol(ecbdata->opt,
DIFF_SYMBOL_CONTEXT_MARKER, line, len, 0);
return;
}
ep += 2; /* skip over @@ */
/* The hunk header in fraginfo color */
if (ecbdata->opt->flags.dual_color_diffed_diffs)
strbuf_addstr(&msgbuf, reverse);
strbuf_addstr(&msgbuf, frag);
if (ecbdata->opt->flags.suppress_hunk_header_line_count)
strbuf_add(&msgbuf, atat, sizeof(atat));
else
strbuf_add(&msgbuf, line, ep - line);
strbuf_addstr(&msgbuf, reset);
/*
* trailing "\r\n"
*/
for ( ; i < 3; i++)
if (line[len - i] == '\r' || line[len - i] == '\n')
len--;
/* blank before the func header */
for (cp = ep; ep - line < len; ep++)
if (*ep != ' ' && *ep != '\t')
break;
if (ep != cp) {
strbuf_addstr(&msgbuf, context);
strbuf_add(&msgbuf, cp, ep - cp);
strbuf_addstr(&msgbuf, reset);
}
if (ep < line + len) {
strbuf_addstr(&msgbuf, func);
strbuf_add(&msgbuf, ep, line + len - ep);
strbuf_addstr(&msgbuf, reset);
}
strbuf_add(&msgbuf, line + len, org_len - len);
strbuf_complete_line(&msgbuf);
emit_diff_symbol(ecbdata->opt,
DIFF_SYMBOL_CONTEXT_FRAGINFO, msgbuf.buf, msgbuf.len, 0);
strbuf_release(&msgbuf);
}
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;
BUG("diff is failing to clean up its tempfiles");
}
static void remove_tempfile(void)
{
int i;
for (i = 0; i < ARRAY_SIZE(diff_temp); i++) {
if (is_tempfile_active(diff_temp[i].tempfile))
delete_tempfile(&diff_temp[i].tempfile);
diff_temp[i].name = NULL;
}
}
static void add_line_count(struct strbuf *out, int count)
{
switch (count) {
case 0:
strbuf_addstr(out, "0,0");
break;
case 1:
strbuf_addstr(out, "1");
break;
default:
strbuf_addf(out, "1,%d", count);
break;
}
}
static void emit_rewrite_lines(struct emit_callback *ecb,
int prefix, const char *data, int size)
{
const char *endp = NULL;
while (0 < size) {
int len;
endp = memchr(data, '\n', size);
len = endp ? (endp - data + 1) : size;
if (prefix != '+') {
ecb->lno_in_preimage++;
emit_del_line(ecb, data, len);
} else {
ecb->lno_in_postimage++;
emit_add_line(ecb, data, len);
}
size -= len;
data += len;
}
if (!endp)
emit_diff_symbol(ecb->opt, DIFF_SYMBOL_NO_LF_EOF, NULL, 0, 0);
}
static void emit_rewrite_diff(const char *name_a,
const char *name_b,
struct diff_filespec *one,
struct diff_filespec *two,
struct userdiff_driver *textconv_one,
struct userdiff_driver *textconv_two,
struct diff_options *o)
{
int lc_a, lc_b;
static struct strbuf a_name = STRBUF_INIT, b_name = STRBUF_INIT;
const char *a_prefix, *b_prefix;
char *data_one, *data_two;
size_t size_one, size_two;
struct emit_callback ecbdata;
struct strbuf out = STRBUF_INIT;
if (diff_mnemonic_prefix && o->flags.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 == '/');
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);
size_one = fill_textconv(o->repo, textconv_one, one, &data_one);
size_two = fill_textconv(o->repo, textconv_two, two, &data_two);
memset(&ecbdata, 0, sizeof(ecbdata));
ecbdata.color_diff = want_color(o->use_color);
ecbdata.ws_rule = whitespace_rule(o->repo->index, name_b);
ecbdata.opt = o;
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);
emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR_MINUS,
a_name.buf, a_name.len, 0);
emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR_PLUS,
b_name.buf, b_name.len, 0);
strbuf_addstr(&out, "@@ -");
if (!o->irreversible_delete)
add_line_count(&out, lc_a);
else
strbuf_addstr(&out, "?,?");
strbuf_addstr(&out, " +");
add_line_count(&out, lc_b);
strbuf_addstr(&out, " @@\n");
emit_diff_symbol(o, DIFF_SYMBOL_REWRITE_DIFF, out.buf, out.len, 0);
strbuf_release(&out);
if (lc_a && !o->irreversible_delete)
emit_rewrite_lines(&ecbdata, '-', data_one, size_one);
if (lc_b)
emit_rewrite_lines(&ecbdata, '+', data_two, size_two);
if (textconv_one)
free((char *)data_one);
if (textconv_two)
free((char *)data_two);
}
struct diff_words_buffer {
mmfile_t text;
unsigned 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_style_elem {
const char *prefix;
const char *suffix;
const char *color; /* NULL; filled in by the setup code if
* color is enabled */
};
struct diff_words_style {
enum diff_words_type type;
struct diff_words_style_elem new_word, old_word, ctx;
const char *newline;
};
static struct diff_words_style diff_words_styles[] = {
{ DIFF_WORDS_PORCELAIN, {"+", "\n"}, {"-", "\n"}, {" ", "\n"}, "~\n" },
{ DIFF_WORDS_PLAIN, {"{+", "+}"}, {"[-", "-]"}, {"", ""}, "\n" },
{ DIFF_WORDS_COLOR, {"", ""}, {"", ""}, {"", ""}, "\n" }
};
struct diff_words_data {
struct diff_words_buffer minus, plus;
const char *current_plus;
int last_minus;
struct diff_options *opt;
regex_t *word_regex;
enum diff_words_type type;
struct diff_words_style *style;
};
static int fn_out_diff_words_write_helper(struct diff_options *o,
struct diff_words_style_elem *st_el,
const char *newline,
size_t count, const char *buf)
{
int print = 0;
struct strbuf sb = STRBUF_INIT;
while (count) {
char *p = memchr(buf, '\n', count);
if (print)
strbuf_addstr(&sb, diff_line_prefix(o));
if (p != buf) {
const char *reset = st_el->color && *st_el->color ?
GIT_COLOR_RESET : NULL;
if (st_el->color && *st_el->color)
strbuf_addstr(&sb, st_el->color);
strbuf_addstr(&sb, st_el->prefix);
strbuf_add(&sb, buf, p ? p - buf : count);
strbuf_addstr(&sb, st_el->suffix);
if (reset)
strbuf_addstr(&sb, reset);
}
if (!p)
goto out;
strbuf_addstr(&sb, newline);
count -= p + 1 - buf;
buf = p + 1;
print = 1;
if (count) {
emit_diff_symbol(o, DIFF_SYMBOL_WORD_DIFF,
sb.buf, sb.len, 0);
strbuf_reset(&sb);
}
}
out:
if (sb.len)
emit_diff_symbol(o, DIFF_SYMBOL_WORD_DIFF,
sb.buf, sb.len, 0);
strbuf_release(&sb);
return 0;
}
/*
* '--color-words' algorithm can be described as:
*
* 1. collect the minus/plus lines of a diff hunk, divided into
* minus-lines and plus-lines;
*
* 2. break both minus-lines and plus-lines into words and
* place them into two mmfile_t with one word for each line;
*
* 3. use xdiff to run diff on the two mmfile_t to get the words level diff;
*
* And for the common parts of the both file, we output the plus side text.
* diff_words->current_plus is used to trace the current position of the plus file
* which printed. diff_words->last_minus is used to trace the last minus word
* printed.
*
* For '--graph' to work with '--color-words', we need to output the graph prefix
* on each line of color words output. Generally, there are two conditions on
* which we should output the prefix.
*
* 1. diff_words->last_minus == 0 &&
* diff_words->current_plus == diff_words->plus.text.ptr
*
* that is: the plus text must start as a new line, and if there is no minus
* word printed, a graph prefix must be printed.
*
* 2. diff_words->current_plus > diff_words->plus.text.ptr &&
* *(diff_words->current_plus - 1) == '\n'
*
* that is: a graph prefix must be printed following a '\n'
*/
static int color_words_output_graph_prefix(struct diff_words_data *diff_words)
{
if ((diff_words->last_minus == 0 &&
diff_words->current_plus == diff_words->plus.text.ptr) ||
(diff_words->current_plus > diff_words->plus.text.ptr &&
*(diff_words->current_plus - 1) == '\n')) {
return 1;
} else {
return 0;
}
}
static void fn_out_diff_words_aux(void *priv,
long minus_first, long minus_len,
long plus_first, long plus_len,
const char *func UNUSED, long funclen UNUSED)
{
struct diff_words_data *diff_words = priv;
struct diff_words_style *style = diff_words->style;
const char *minus_begin, *minus_end, *plus_begin, *plus_end;
struct diff_options *opt = diff_words->opt;
const char *line_prefix;
assert(opt);
line_prefix = diff_line_prefix(opt);
/* 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 (color_words_output_graph_prefix(diff_words)) {
fputs(line_prefix, diff_words->opt->file);
}
if (diff_words->current_plus != plus_begin) {
fn_out_diff_words_write_helper(diff_words->opt,
&style->ctx, style->newline,
plus_begin - diff_words->current_plus,
diff_words->current_plus);
}
if (minus_begin != minus_end) {
fn_out_diff_words_write_helper(diff_words->opt,
&style->old_word, style->newline,
minus_end - minus_begin, minus_begin);
}
if (plus_begin != plus_end) {
fn_out_diff_words_write_helper(diff_words->opt,
&style->new_word, style->newline,
plus_end - plus_begin, plus_begin);
}
diff_words->current_plus = plus_end;
diff_words->last_minus = minus_first;
}
/* 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)
{
while (word_regex && *begin < buffer->size) {
regmatch_t match[1];
if (!regexec_buf(word_regex, buffer->ptr + *begin,
buffer->size - *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;
if (*begin == *end)
(*begin)++;
else
return *begin > *end;
} else {
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;
mmfile_t minus, plus;
struct diff_words_style *style = diff_words->style;
struct diff_options *opt = diff_words->opt;
const char *line_prefix;
assert(opt);
line_prefix = diff_line_prefix(opt);
/* special case: only removal */
if (!diff_words->plus.text.size) {
emit_diff_symbol(diff_words->opt, DIFF_SYMBOL_WORD_DIFF,
line_prefix, strlen(line_prefix), 0);
fn_out_diff_words_write_helper(diff_words->opt,
&style->old_word, style->newline,
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;
diff_words->last_minus = 0;
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 = 0;
/* as only the hunk header will be parsed, we need a 0-context */
xecfg.ctxlen = 0;
if (xdi_diff_outf(&minus, &plus, fn_out_diff_words_aux, NULL,
diff_words, &xpp, &xecfg))
die("unable to generate word diff");
free(minus.ptr);
free(plus.ptr);
if (diff_words->current_plus != diff_words->plus.text.ptr +
diff_words->plus.text.size) {
if (color_words_output_graph_prefix(diff_words))
emit_diff_symbol(diff_words->opt, DIFF_SYMBOL_WORD_DIFF,
line_prefix, strlen(line_prefix), 0);
fn_out_diff_words_write_helper(diff_words->opt,
&style->ctx, style->newline,
diff_words->plus.text.ptr + diff_words->plus.text.size
- diff_words->current_plus, diff_words->current_plus);
}
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)
{
struct diff_options *wo = ecbdata->diff_words->opt;
if (ecbdata->diff_words->minus.text.size ||
ecbdata->diff_words->plus.text.size)
diff_words_show(ecbdata->diff_words);
if (wo->emitted_symbols) {
struct diff_options *o = ecbdata->opt;
struct emitted_diff_symbols *wol = wo->emitted_symbols;
int i;
/*
* NEEDSWORK:
* Instead of appending each, concat all words to a line?
*/
for (i = 0; i < wol->nr; i++)
append_emitted_diff_symbol(o, &wol->buf[i]);
for (i = 0; i < wol->nr; i++)
free((void *)wol->buf[i].line);
wol->nr = 0;
}
}
static void diff_filespec_load_driver(struct diff_filespec *one,
struct index_state *istate)
{
/* Use already-loaded driver */
if (one->driver)
return;
if (S_ISREG(one->mode))
one->driver = userdiff_find_by_path(istate, one->path);
/* Fallback to default settings */
if (!one->driver)
one->driver = userdiff_find_by_name("default");
}
static const char *userdiff_word_regex(struct diff_filespec *one,
struct index_state *istate)
{
diff_filespec_load_driver(one, istate);
return one->driver->word_regex;
}
static void init_diff_words_data(struct emit_callback *ecbdata,
struct diff_options *orig_opts,
struct diff_filespec *one,
struct diff_filespec *two)
{
int i;
struct diff_options *o = xmalloc(sizeof(struct diff_options));
memcpy(o, orig_opts, sizeof(struct diff_options));
CALLOC_ARRAY(ecbdata->diff_words, 1);
ecbdata->diff_words->type = o->word_diff;
ecbdata->diff_words->opt = o;
if (orig_opts->emitted_symbols)
CALLOC_ARRAY(o->emitted_symbols, 1);
if (!o->word_regex)
o->word_regex = userdiff_word_regex(one, o->repo->index);
if (!o->word_regex)
o->word_regex = userdiff_word_regex(two, o->repo->index);
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);
}
for (i = 0; i < ARRAY_SIZE(diff_words_styles); i++) {
if (o->word_diff == diff_words_styles[i].type) {
ecbdata->diff_words->style =
&diff_words_styles[i];
break;
}
}
if (want_color(o->use_color)) {
struct diff_words_style *st = ecbdata->diff_words->style;
st->old_word.color = diff_get_color_opt(o, DIFF_FILE_OLD);
st->new_word.color = diff_get_color_opt(o, DIFF_FILE_NEW);
st->ctx.color = diff_get_color_opt(o, DIFF_CONTEXT);
}
}
static void free_diff_words_data(struct emit_callback *ecbdata)
{
if (ecbdata->diff_words) {
diff_words_flush(ecbdata);
free_emitted_diff_symbols(ecbdata->diff_words->opt->emitted_symbols);
free (ecbdata->diff_words->opt);
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);
if (ecbdata->diff_words->word_regex) {
regfree(ecbdata->diff_words->word_regex);
free(ecbdata->diff_words->word_regex);
}
FREE_AND_NULL(ecbdata->diff_words);
}
}
const char *diff_get_color(int diff_use_color, enum color_diff ix)
{
if (want_color(diff_use_color))
return diff_colors[ix];
return "";
}
const char *diff_line_prefix(struct diff_options *opt)
{
struct strbuf *msgbuf;
if (!opt->output_prefix)
return "";
msgbuf = opt->output_prefix(opt, opt->output_prefix_data);
return msgbuf->buf;
}
static unsigned long sane_truncate_line(char *line, unsigned long len)
{
const char *cp;
unsigned long allot;
size_t l = 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 int fn_out_consume(void *priv, char *line, unsigned long len)
{
struct emit_callback *ecbdata = priv;
struct diff_options *o = ecbdata->opt;
o->found_changes = 1;
if (ecbdata->header) {
emit_diff_symbol(o, DIFF_SYMBOL_HEADER,
ecbdata->header->buf, ecbdata->header->len, 0);
strbuf_reset(ecbdata->header);
ecbdata->header = NULL;
}
if (ecbdata->label_path[0]) {
emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR_MINUS,
ecbdata->label_path[0],
strlen(ecbdata->label_path[0]), 0);
emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR_PLUS,
ecbdata->label_path[1],
strlen(ecbdata->label_path[1]), 0);
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(line, len);
find_lno(line, ecbdata);
emit_hunk_header(ecbdata, line, len);
return 0;
}
if (ecbdata->diff_words) {
enum diff_symbol s =
ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN ?
DIFF_SYMBOL_WORDS_PORCELAIN : DIFF_SYMBOL_WORDS;
if (line[0] == '-') {
diff_words_append(line, len,
&ecbdata->diff_words->minus);
return 0;
} else if (line[0] == '+') {
diff_words_append(line, len,
&ecbdata->diff_words->plus);
return 0;
} else if (starts_with(line, "\\ ")) {
/*
* Eat the "no newline at eof" marker as if we
* saw a "+" or "-" line with nothing on it,
* and return without diff_words_flush() to
* defer processing. If this is the end of
* preimage, more "+" lines may come after it.
*/
return 0;
}
diff_words_flush(ecbdata);
emit_diff_symbol(o, s, line, len, 0);
return 0;
}
switch (line[0]) {
case '+':
ecbdata->lno_in_postimage++;
emit_add_line(ecbdata, line + 1, len - 1);
break;
case '-':
ecbdata->lno_in_preimage++;
emit_del_line(ecbdata, line + 1, len - 1);
break;
case ' ':
ecbdata->lno_in_postimage++;
ecbdata->lno_in_preimage++;
emit_context_line(ecbdata, line + 1, len - 1);
break;
default:
/* incomplete line at the end */
ecbdata->lno_in_preimage++;
emit_diff_symbol(o, DIFF_SYMBOL_CONTEXT_INCOMPLETE,
line, len, 0);
break;
}
return 0;
}
static void pprint_rename(struct strbuf *name, const char *a, const char *b)
{
const char *old_name = a;
const char *new_name = b;
int pfx_length, sfx_length;
int pfx_adjust_for_slash;
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;
}
/* Find common prefix */
pfx_length = 0;
while (*old_name && *new_name && *old_name == *new_name) {
if (*old_name == '/')
pfx_length = old_name - a + 1;
old_name++;
new_name++;
}
/* Find common suffix */
old_name = a + len_a;
new_name = b + len_b;
sfx_length = 0;
/*
* If there is a common prefix, it must end in a slash. In
* that case we let this loop run 1 into the prefix to see the
* same slash.
*
* If there is no common prefix, we cannot do this as it would
* underrun the input strings.
*/
pfx_adjust_for_slash = (pfx_length ? 1 : 0);
while (a + pfx_length - pfx_adjust_for_slash <= old_name &&
b + pfx_length - pfx_adjust_for_slash <= new_name &&
*old_name == *new_name) {
if (*old_name == '/')
sfx_length = len_a - (old_name - a);
old_name--;
new_name--;
}
/*
* 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);
}
}
static struct diffstat_file *diffstat_add(struct diffstat_t *diffstat,
const char *name_a,
const char *name_b)
{
struct diffstat_file *x;
CALLOC_ARRAY(x, 1);
ALLOC_GROW(diffstat->files, diffstat->nr + 1, diffstat->alloc);
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 int diffstat_consume(void *priv, char *line, unsigned long len)
{
struct diffstat_t *diffstat = priv;
struct diffstat_file *x = diffstat->files[diffstat->nr - 1];
if (!len)
BUG("xdiff fed us an empty line");
if (line[0] == '+')
x->added++;
else if (line[0] == '-')
x->deleted++;
return 0;
}
const char mime_boundary_leader[] = "------------";
static int scale_linear(int it, int width, int max_change)
{
if (!it)
return 0;
/*
* make sure that at least one '-' or '+' is printed if
* there is any change to this path. The easiest way is to
* scale linearly as if the allotted width is one column shorter
* than it is, and then add 1 to the result.
*/
return 1 + (it * (width - 1) / max_change);
}
static void show_graph(struct strbuf *out, char ch, int cnt,
const char *set, const char *reset)
{
if (cnt <= 0)
return;
strbuf_addstr(out, set);
strbuf_addchars(out, ch, cnt);
strbuf_addstr(out, reset);
}
static void fill_print_name(struct diffstat_file *file)
{
struct strbuf pname = STRBUF_INIT;
if (file->print_name)
return;
if (file->is_renamed)
pprint_rename(&pname, file->from_name, file->name);
else
quote_c_style(file->name, &pname, NULL, 0);
if (file->comments)
strbuf_addf(&pname, " (%s)", file->comments);
file->print_name = strbuf_detach(&pname, NULL);
}
static void print_stat_summary_inserts_deletes(struct diff_options *options,
int files, int insertions, int deletions)
{
struct strbuf sb = STRBUF_INIT;
if (!files) {
assert(insertions == 0 && deletions == 0);
emit_diff_symbol(options, DIFF_SYMBOL_STATS_SUMMARY_NO_FILES,
NULL, 0, 0);
return;
}
strbuf_addf(&sb,
(files == 1) ? " %d file changed" : " %d files changed",
files);
/*
* For binary diff, the caller may want to print "x files
* changed" with insertions == 0 && deletions == 0.
*
* Not omitting "0 insertions(+), 0 deletions(-)" in this case
* is probably less confusing (i.e skip over "2 files changed
* but nothing about added/removed lines? Is this a bug in Git?").
*/
if (insertions || deletions == 0) {
strbuf_addf(&sb,
(insertions == 1) ? ", %d insertion(+)" : ", %d insertions(+)",
insertions);
}
if (deletions || insertions == 0) {
strbuf_addf(&sb,
(deletions == 1) ? ", %d deletion(-)" : ", %d deletions(-)",
deletions);
}
strbuf_addch(&sb, '\n');
emit_diff_symbol(options, DIFF_SYMBOL_STATS_SUMMARY_INSERTS_DELETES,
sb.buf, sb.len, 0);
strbuf_release(&sb);
}
void print_stat_summary(FILE *fp, int files,
int insertions, int deletions)
{
struct diff_options o;
memset(&o, 0, sizeof(o));
o.file = fp;
print_stat_summary_inserts_deletes(&o, files, insertions, deletions);
}
static void show_stats(struct diffstat_t *data, struct diff_options *options)
{
int i, len, add, del, adds = 0, dels = 0;
uintmax_t max_change = 0, max_len = 0;
int total_files = data->nr, count;
int width, name_width, graph_width, number_width = 0, bin_width = 0;
const char *reset, *add_c, *del_c;
int extra_shown = 0;
const char *line_prefix = diff_line_prefix(options);
struct strbuf out = STRBUF_INIT;
if (data->nr == 0)
return;
count = options->stat_count ? options->stat_count : data->nr;
reset = diff_get_color_opt(options, DIFF_RESET);
add_c = diff_get_color_opt(options, DIFF_FILE_NEW);
del_c = diff_get_color_opt(options, DIFF_FILE_OLD);
/*
* Find the longest filename and max number of changes
*/
for (i = 0; (i < count) && (i < data->nr); i++) {
struct diffstat_file *file = data->files[i];
uintmax_t change = file->added + file->deleted;
if (!file->is_interesting && (change == 0)) {
count++; /* not shown == room for one more */
continue;
}
fill_print_name(file);
len = utf8_strwidth(file->print_name);
if (max_len < len)
max_len = len;
if (file->is_unmerged) {
/* "Unmerged" is 8 characters */
bin_width = bin_width < 8 ? 8 : bin_width;
continue;
}
if (file->is_binary) {
/* "Bin XXX -> YYY bytes" */
int w = 14 + decimal_width(file->added)
+ decimal_width(file->deleted);
bin_width = bin_width < w ? w : bin_width;
/* Display change counts aligned with "Bin" */
number_width = 3;
continue;
}
if (max_change < change)
max_change = change;
}
count = i; /* where we can stop scanning in data->files[] */
/*
* We have width = stat_width or term_columns() columns total.
* We want a maximum of min(max_len, stat_name_width) for the name part.
* We want a maximum of min(max_change, stat_graph_width) for the +- part.
* We also need 1 for " " and 4 + decimal_width(max_change)
* for " | NNNN " and one the empty column at the end, altogether
* 6 + decimal_width(max_change).
*
* If there's not enough space, we will use the smaller of
* stat_name_width (if set) and 5/8*width for the filename,
* and the rest for constant elements + graph part, but no more
* than stat_graph_width for the graph part.
* (5/8 gives 50 for filename and 30 for the constant parts + graph
* for the standard terminal size).
*
* In other words: stat_width limits the maximum width, and
* stat_name_width fixes the maximum width of the filename,
* and is also used to divide available columns if there
* aren't enough.
*
* Binary files are displayed with "Bin XXX -> YYY bytes"
* instead of the change count and graph. This part is treated
* similarly to the graph part, except that it is not
* "scaled". If total width is too small to accommodate the
* guaranteed minimum width of the filename part and the
* separators and this message, this message will "overflow"
* making the line longer than the maximum width.
*/
/*
* NEEDSWORK: line_prefix is often used for "log --graph" output
* and contains ANSI-colored string. utf8_strnwidth() should be
* used to correctly count the display width instead of strlen().
*/
if (options->stat_width == -1)
width = term_columns() - strlen(line_prefix);
else
width = options->stat_width ? options->stat_width : 80;
number_width = decimal_width(max_change) > number_width ?
decimal_width(max_change) : number_width;
if (options->stat_graph_width == -1)
options->stat_graph_width = diff_stat_graph_width;
/*
* Guarantee 3/8*16==6 for the graph part
* and 5/8*16==10 for the filename part
*/
if (width < 16 + 6 + number_width)
width = 16 + 6 + number_width;
/*
* First assign sizes that are wanted, ignoring available width.
* strlen("Bin XXX -> YYY bytes") == bin_width, and the part
* starting from "XXX" should fit in graph_width.
*/
graph_width = max_change + 4 > bin_width ? max_change : bin_width - 4;
if (options->stat_graph_width &&
options->stat_graph_width < graph_width)
graph_width = options->stat_graph_width;
name_width = (options->stat_name_width > 0 &&
options->stat_name_width < max_len) ?
options->stat_name_width : max_len;
/*
* Adjust adjustable widths not to exceed maximum width
*/
if (name_width + number_width + 6 + graph_width > width) {
if (graph_width > width * 3/8 - number_width - 6) {
graph_width = width * 3/8 - number_width - 6;
if (graph_width < 6)
graph_width = 6;
}
if (options->stat_graph_width &&
graph_width > options->stat_graph_width)
graph_width = options->stat_graph_width;
if (name_width > width - number_width - 6 - graph_width)
name_width = width - number_width - 6 - graph_width;
else
graph_width = width - number_width - 6 - name_width;
}
/*
* From here name_width is the width of the name area,
* and graph_width is the width of the graph area.
* max_change is used to scale graph properly.
*/
for (i = 0; i < count; i++) {
const char *prefix = "";
struct diffstat_file *file = data->files[i];
char *name = file->print_name;
uintmax_t added = file->added;
uintmax_t deleted = file->deleted;
int name_len, padding;
if (!file->is_interesting && (added + deleted == 0))
continue;
/*
* "scale" the filename
*/
len = name_width;
name_len = utf8_strwidth(name);
if (name_width < name_len) {
char *slash;
prefix = "...";
len -= 3;
/*
* NEEDSWORK: (name_len - len) counts the display
* width, which would be shorter than the byte
* length of the corresponding substring.
* Advancing "name" by that number of bytes does
* *NOT* skip over that many columns, so it is
* very likely that chomping the pathname at the
* slash we will find starting from "name" will
* leave the resulting string still too long.
*/
name += name_len - len;
slash = strchr(name, '/');
if (slash)
name = slash;
}
padding = len - utf8_strwidth(name);
if (padding < 0)
padding = 0;
if (file->is_binary) {
strbuf_addf(&out, " %s%s%*s | %*s",
prefix, name, padding, "",
number_width, "Bin");
if (!added && !deleted) {
strbuf_addch(&out, '\n');
emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE,
out.buf, out.len, 0);
strbuf_reset(&out);
continue;
}
strbuf_addf(&out, " %s%"PRIuMAX"%s",
del_c, deleted, reset);
strbuf_addstr(&out, " -> ");
strbuf_addf(&out, "%s%"PRIuMAX"%s",
add_c, added, reset);
strbuf_addstr(&out, " bytes\n");
emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE,
out.buf, out.len, 0);
strbuf_reset(&out);
continue;
}
else if (file->is_unmerged) {
strbuf_addf(&out, " %s%s%*s | %*s",
prefix, name, padding, "",
number_width, "Unmerged");
emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE,
out.buf, out.len, 0);
strbuf_reset(&out);
continue;
}
/*
* scale the add/delete
*/
add = added;
del = deleted;
if (graph_width <= max_change) {
int total = scale_linear(add + del, graph_width, max_change);
if (total < 2 && add && del)
/* width >= 2 due to the sanity check */
total = 2;
if (add < del) {
add = scale_linear(add, graph_width, max_change);
del = total - add;
} else {
del = scale_linear(del, graph_width, max_change);
add = total - del;
}
}
strbuf_addf(&out, " %s%s%*s | %*"PRIuMAX"%s",
prefix, name, padding, "",
number_width, added + deleted,
added + deleted ? " " : "");
show_graph(&out, '+', add, add_c, reset);
show_graph(&out, '-', del, del_c, reset);
strbuf_addch(&out, '\n');
emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE,
out.buf, out.len, 0);
strbuf_reset(&out);
}
for (i = 0; i < data->nr; i++) {
struct diffstat_file *file = data->files[i];
uintmax_t added = file->added;
uintmax_t deleted = file->deleted;
if (file->is_unmerged ||
(!file->is_interesting && (added + deleted == 0))) {
total_files--;
continue;
}
if (!file->is_binary) {
adds += added;
dels += deleted;
}
if (i < count)
continue;
if (!extra_shown)
emit_diff_symbol(options,
DIFF_SYMBOL_STATS_