Merge branch 'mm/line-log-limited-ops' into seen

The 'git log -L<range>:<path>' command has been taught to limit
various 'diff' operations, such as '--stat', '--check', and '-G', to
the specified range and path.

* mm/line-log-limited-ops:
  diffcore-pickaxe: scope -G to the -L tracked range
  diff: support --check with -L line ranges
  line-log: support diff stat formats with -L
  diff: extract a line-range diff helper for reuse
  diff: emit -L hunk headers via xdiff's formatter
  diff: simplify the line-range filter by classifying removals immediately
  diff: rename and group the line-range filter for clarity
This commit is contained in:
Junio C Hamano
2026-07-23 12:57:55 -07:00
11 changed files with 827 additions and 228 deletions

493
diff.c
View File

@@ -610,28 +610,74 @@ struct emit_callback {
};
/*
* State for the line-range callback wrappers that sit between
* xdi_diff_outf() and fn_out_consume(). xdiff produces a normal,
* unfiltered diff; the wrappers intercept each hunk header and line,
* track post-image position, and forward only lines that fall within
* the requested ranges. Contiguous in-range lines are collected into
* range hunks and flushed with a synthetic @@ header so that
* fn_out_consume() sees well-formed unified-diff fragments.
* Line-range filter: scopes "git log -L" output to the tracked ranges.
*
* Removal lines ('-') cannot be classified by post-image position, so
* they are buffered in pending_rm until the next '+' or ' ' line
* reveals whether they precede an in-range line (flush into range hunk) or
* an out-of-range line (discard).
* It sits between xdi_diff_outf() and an output callback (fn_out_consume,
* diffstat_consume, checkdiff_consume). xdiff produces a normal diff; the
* filter forwards only the lines inside the requested ranges, collecting
* contiguous in-range lines into a "range hunk" emitted with a synthetic
* @@ header so the callback sees well-formed unified-diff fragments.
*
* A diff describes the change from a pre-image to a post-image. Each
* line is context (' ', in both), a removal ('-', pre-image only), or
* an addition ('+', post-image only). -L tracks ranges in the
* post-image, so a line is in range by its post-image position.
*
* Two 1-based cursors track the next line in each image, named as in
* struct emit_callback and seeded from the xdiff hunk header:
*
* lno_in_postimage advances on '+' and ' ' (lines in the post-image)
* lno_in_preimage advances on '-' and ' ' (lines in the pre-image)
*
* Ranges are 0-based half-open [start, end), so a line is tested at the
* 0-based index idx_in_postimage = lno_in_postimage - 1.
*
* A '-' is not present in the post-image, so it has no post-image line
* number of its own. Since it does not advance lno_in_postimage, it is
* classified at the idx_in_postimage that the following '+'/' ' will
* occupy. xdiff emits a change's removals before its additions, so that
* index is already known when the '-' arrives.
*
* The synthetic "@@ -<old> +<new> @@" header has two sides, old (the
* pre-image) and new (the post-image), matching the xdiff_emit_hunk_fn
* callback; the hunk.old_begin / hunk.new_begin fields below hold those
* begins, and flush_range_hunk() derives the counts from the buffered
* lines.
*
* Example, tracking post-image line 2 (range [1, 2)) of:
*
* pre-image post-image
* 1 a 1 a
* 2 b 2 X (b -> X)
* 3 c 3 c
*
* classify each line by idx_in_postimage. The pre and post columns
* are each cursor's value while that line is classified, i.e. before
* the line advances them (pre = lno_in_preimage,
* post = lno_in_postimage, idx = idx_in_postimage):
* ' a' pre 1 post 1 idx 0 -> before start, skip
* '-b' pre 2 post 2 idx 1 -> keep (removal)
* '+X' pre 3 post 2 idx 1 -> keep (addition)
* ' c' pre 3 post 3 idx 2 -> past end, flush
*
* -b and +X share idx = 1 because -b did not advance lno_in_postimage;
* both land in the range hunk, flushed when ' c' crosses the range end.
*/
struct line_range_callback {
struct line_range_filter {
xdiff_emit_line_fn orig_line_fn;
/*
* Optional; consumers that report file line numbers (e.g.
* checkdiff) need the synthetic hunk header to set their
* post-image position before in-range lines are replayed.
*/
xdiff_emit_hunk_fn orig_hunk_fn;
void *orig_cb_data;
const struct range_set *ranges; /* 0-based [start, end) */
unsigned int cur_range; /* index into the range_set */
/* Post/pre-image line counters (1-based, set from hunk headers) */
long lno_post;
long lno_pre;
long lno_in_postimage;
long lno_in_preimage;
/*
* Function name from most recent xdiff hunk header;
@@ -640,17 +686,17 @@ struct line_range_callback {
char func[80];
long funclen;
/* Range hunk being accumulated for the current range */
struct strbuf rhunk;
long rhunk_old_begin, rhunk_old_count;
long rhunk_new_begin, rhunk_new_count;
int rhunk_active;
int rhunk_has_changes; /* any '+' or '-' lines? */
/* Removal lines not yet known to be in-range */
struct strbuf pending_rm;
int pending_rm_count;
long pending_rm_pre_begin; /* pre-image line of first pending */
/*
* The range hunk being accumulated. At most one is live at a time:
* it is flushed and reset as the cursor leaves each range (and once
* more at end of diff), then reused for the next range.
*/
struct {
struct strbuf lines; /* buffered in-range diff lines */
long old_begin;
long new_begin;
int active;
} hunk;
int ret; /* latched error from orig_line_fn */
};
@@ -2540,26 +2586,60 @@ static int quick_consume(void *priv, char *line UNUSED, unsigned long len UNUSED
return 1;
}
static void discard_pending_rm(struct line_range_callback *s)
static void line_range_filter_init(struct line_range_filter *filter,
const struct range_set *ranges,
xdiff_emit_line_fn line_fn,
void *cb_data)
{
strbuf_reset(&s->pending_rm);
s->pending_rm_count = 0;
memset(filter, 0, sizeof(*filter));
filter->orig_line_fn = line_fn;
filter->orig_cb_data = cb_data;
filter->ranges = ranges;
strbuf_init(&filter->hunk.lines, 0);
}
static void flush_rhunk(struct line_range_callback *s)
/*
* Begin a range hunk at the first in-range line. Its position fixes the
* hunk's begins, taken from the two image cursors before they advance:
* new_begin from the post-image, old_begin from the pre-image. The line
* counts are not tracked here; flush_range_hunk() derives them from the
* buffered lines.
*/
static void begin_range_hunk(struct line_range_filter *filter)
{
filter->hunk.active = 1;
filter->hunk.new_begin = filter->lno_in_postimage;
filter->hunk.old_begin = filter->lno_in_preimage;
strbuf_reset(&filter->hunk.lines);
}
static void flush_range_hunk(struct line_range_filter *filter)
{
struct strbuf hdr = STRBUF_INIT;
const char *p, *end;
long old_count = 0, new_count = 0;
int has_changes = 0;
if (!s->rhunk_active || s->ret)
if (!filter->hunk.active || filter->ret)
return;
/* Drain any pending removal lines into the range hunk */
if (s->pending_rm_count) {
strbuf_addbuf(&s->rhunk, &s->pending_rm);
s->rhunk_old_count += s->pending_rm_count;
s->rhunk_has_changes = 1;
discard_pending_rm(s);
/*
* Derive the hunk's geometry from the buffered lines: a ' '
* counts on both sides, a '-' on the old side, a '+' on the new.
* A '-' or '+' marks a real change; the "\ No newline at end of
* file" marker (line[0] == '\\') counts on neither side.
*/
p = filter->hunk.lines.buf;
end = p + filter->hunk.lines.len;
while (p < end) {
const char *eol = memchr(p, '\n', end - p);
if (*p == ' ' || *p == '-')
old_count++;
if (*p == ' ' || *p == '+')
new_count++;
if (*p == '-' || *p == '+')
has_changes = 1;
p = eol ? eol + 1 : end;
}
/*
@@ -2568,22 +2648,28 @@ static void flush_rhunk(struct line_range_callback *s)
* ctxlen causes xdiff to emit context covering a range that
* has no changes in this commit.
*/
if (!s->rhunk_has_changes) {
s->rhunk_active = 0;
strbuf_reset(&s->rhunk);
if (!has_changes) {
filter->hunk.active = 0;
strbuf_reset(&filter->hunk.lines);
return;
}
strbuf_addf(&hdr, "@@ -%ld,%ld +%ld,%ld @@",
s->rhunk_old_begin, s->rhunk_old_count,
s->rhunk_new_begin, s->rhunk_new_count);
if (s->funclen > 0) {
strbuf_addch(&hdr, ' ');
strbuf_add(&hdr, s->func, s->funclen);
}
strbuf_addch(&hdr, '\n');
xdiff_emit_hunk_header(&hdr, filter->hunk.old_begin, old_count,
filter->hunk.new_begin, new_count,
filter->func, filter->funclen);
s->ret = s->orig_line_fn(s->orig_cb_data, hdr.buf, hdr.len);
/*
* Inform a line-numbering consumer of the post-image position
* before replaying lines, mirroring the hunk callback xdiff
* would have issued for a non-scoped diff.
*/
if (filter->orig_hunk_fn)
filter->orig_hunk_fn(filter->orig_cb_data,
filter->hunk.old_begin, old_count,
filter->hunk.new_begin, new_count,
filter->func, filter->funclen);
filter->ret = filter->orig_line_fn(filter->orig_cb_data, hdr.buf, hdr.len);
strbuf_release(&hdr);
/*
@@ -2591,135 +2677,159 @@ static void flush_rhunk(struct line_range_callback *s)
* The cast discards const because xdiff_emit_line_fn takes
* char *, though fn_out_consume does not modify the buffer.
*/
p = s->rhunk.buf;
end = p + s->rhunk.len;
while (!s->ret && p < end) {
p = filter->hunk.lines.buf;
end = p + filter->hunk.lines.len;
while (!filter->ret && p < end) {
const char *eol = memchr(p, '\n', end - p);
unsigned long line_len = eol ? (unsigned long)(eol - p + 1)
: (unsigned long)(end - p);
s->ret = s->orig_line_fn(s->orig_cb_data, (char *)p, line_len);
filter->ret = filter->orig_line_fn(filter->orig_cb_data, (char *)p, line_len);
p += line_len;
}
s->rhunk_active = 0;
strbuf_reset(&s->rhunk);
filter->hunk.active = 0;
strbuf_reset(&filter->hunk.lines);
}
static void line_range_hunk_fn(void *data,
long old_begin, long old_nr UNUSED,
long new_begin, long new_nr UNUSED,
long old_begin, long old_nr,
long new_begin, long new_nr,
const char *func, long funclen)
{
struct line_range_callback *s = data;
struct line_range_filter *filter = data;
/*
* When count > 0, begin is 1-based. When count == 0, begin is
* adjusted down by 1 by xdl_emit_hunk_hdr(), but no lines of
* that type will arrive, so the value is unused.
*
* Any pending removal lines from the previous xdiff hunk are
* intentionally left in pending_rm: the line callback will
* flush or discard them when the next content line reveals
* whether the removals precede in-range content.
* Seed the per-image line cursors from the hunk header's begins. For
* a side with no lines (count 0), xdiff's callback has already moved
* its begin to the line before the change, so add one back to recover
* the true 1-based start. xdiff_emit_hunk_header() reapplies that -1
* when the clipped hunk is emitted.
*/
s->lno_post = new_begin;
s->lno_pre = old_begin;
filter->lno_in_postimage = new_nr ? new_begin : new_begin + 1;
filter->lno_in_preimage = old_nr ? old_begin : old_begin + 1;
if (funclen > 0) {
if (funclen > (long)sizeof(s->func))
funclen = sizeof(s->func);
memcpy(s->func, func, funclen);
if (funclen > (long)sizeof(filter->func))
funclen = sizeof(filter->func);
memcpy(filter->func, func, funclen);
}
s->funclen = funclen;
filter->funclen = funclen;
}
static int line_range_line_fn(void *priv, char *line, unsigned long len)
{
struct line_range_callback *s = priv;
const struct range *cur;
long lno_0, cur_pre;
struct line_range_filter *filter = priv;
long idx_in_postimage;
int in_range;
if (s->ret)
return s->ret;
if (line[0] == '-') {
if (!s->pending_rm_count)
s->pending_rm_pre_begin = s->lno_pre;
s->lno_pre++;
strbuf_add(&s->pending_rm, line, len);
s->pending_rm_count++;
return s->ret;
}
if (filter->ret)
return filter->ret;
if (line[0] == '\\') {
if (s->pending_rm_count)
strbuf_add(&s->pending_rm, line, len);
else if (s->rhunk_active)
strbuf_add(&s->rhunk, line, len);
/* otherwise outside tracked range; drop silently */
return s->ret;
if (filter->hunk.active)
strbuf_add(&filter->hunk.lines, line, len);
return filter->ret;
}
if (line[0] != '+' && line[0] != ' ')
if (line[0] != '+' && line[0] != ' ' && line[0] != '-')
BUG("unexpected diff line type '%c'", line[0]);
lno_0 = s->lno_post - 1;
cur_pre = s->lno_pre; /* save before advancing for context lines */
s->lno_post++;
if (line[0] == ' ')
s->lno_pre++;
/*
* idx_in_postimage is this line's 0-based post-image index (see the model on
* struct line_range_filter). The cursors are advanced only after
* the line is classified, so a '-' is tested at the same idx_in_postimage as
* the '+'/' ' that follows it.
*/
idx_in_postimage = filter->lno_in_postimage - 1;
/* Advance past ranges we've passed */
while (s->cur_range < s->ranges->nr &&
lno_0 >= s->ranges->ranges[s->cur_range].end) {
if (s->rhunk_active)
flush_rhunk(s);
discard_pending_rm(s);
s->cur_range++;
/* Retire ranges we have passed, flushing the one we leave. */
while (filter->cur_range < filter->ranges->nr &&
idx_in_postimage >= filter->ranges->ranges[filter->cur_range].end) {
if (filter->hunk.active)
flush_range_hunk(filter);
filter->cur_range++;
}
/* Past all ranges */
if (s->cur_range >= s->ranges->nr) {
discard_pending_rm(s);
return s->ret;
in_range = filter->cur_range < filter->ranges->nr &&
idx_in_postimage >= filter->ranges->ranges[filter->cur_range].start &&
idx_in_postimage < filter->ranges->ranges[filter->cur_range].end;
if (in_range) {
if (!filter->hunk.active)
begin_range_hunk(filter);
strbuf_add(&filter->hunk.lines, line, len);
}
cur = &s->ranges->ranges[s->cur_range];
/*
* Advance each image's cursor: a line present in that image (see
* the model) consumes one of its line numbers.
*/
if (line[0] != '-')
filter->lno_in_postimage++;
if (line[0] != '+')
filter->lno_in_preimage++;
/* Before current range */
if (lno_0 < cur->start) {
discard_pending_rm(s);
return s->ret;
return filter->ret;
}
/*
* Run an xdiff pass through an initialized line-range filter, flush the
* final range hunk, and release the filter. Inflates ctxlen to the largest
* range span first, so that every change within a single range lands in one
* xdiff hunk and the inter-change context is emitted; the filter then clips
* back to range boundaries. The optimal ctxlen depends on where changes fall
* within the range, which is only known after xdiff runs, so the max span is
* the upper bound that guarantees correctness in a single pass. Every
* consumer (patch, diffstat, check) relies on one xdiff hunk per range, so
* this lives here rather than at each call site. Also clears
* XDL_EMIT_NO_HUNK_HDR: the filter seeds its per-image position from the hunk
* headers, so a consumer that otherwise suppresses them (diffstat) still gets
* them here. Returns non-zero if xdiff or any forwarded callback failed.
*/
static int line_range_filter_diff(struct line_range_filter *filter,
mmfile_t *mf1, mmfile_t *mf2,
xpparam_t *xpp, xdemitconf_t *xecfg)
{
const struct range_set *ranges = filter->ranges;
long max_span = 0;
unsigned int i;
int ret;
for (i = 0; i < ranges->nr; i++) {
long span = ranges->ranges[i].end - ranges->ranges[i].start;
if (span > max_span)
max_span = span;
}
if (max_span > xecfg->ctxlen)
xecfg->ctxlen = max_span;
/* In range so start a new range hunk if needed */
if (!s->rhunk_active) {
s->rhunk_active = 1;
s->rhunk_has_changes = 0;
s->rhunk_new_begin = lno_0 + 1;
s->rhunk_old_begin = s->pending_rm_count
? s->pending_rm_pre_begin : cur_pre;
s->rhunk_old_count = 0;
s->rhunk_new_count = 0;
strbuf_reset(&s->rhunk);
/* the filter seeds its per-image position from hunk headers */
xecfg->flags &= ~XDL_EMIT_NO_HUNK_HDR;
ret = xdi_diff_outf(mf1, mf2, line_range_hunk_fn,
line_range_line_fn, filter, xpp, xecfg);
if (!ret) {
flush_range_hunk(filter);
ret = filter->ret;
}
strbuf_release(&filter->hunk.lines);
return ret;
}
/* Flush pending removals into range hunk */
if (s->pending_rm_count) {
strbuf_addbuf(&s->rhunk, &s->pending_rm);
s->rhunk_old_count += s->pending_rm_count;
s->rhunk_has_changes = 1;
discard_pending_rm(s);
}
/*
* Expose the in-file line-range filter to callers outside diff.c (e.g.
* pickaxe -G); see xdiff-interface.h for the contract.
*/
int diff_emit_line_ranges(mmfile_t *one, mmfile_t *two,
const struct range_set *ranges,
xdiff_emit_line_fn line_fn, void *cb_data,
xpparam_t *xpp, xdemitconf_t *xecfg)
{
struct line_range_filter filter;
strbuf_add(&s->rhunk, line, len);
s->rhunk_new_count++;
if (line[0] == '+')
s->rhunk_has_changes = 1;
else
s->rhunk_old_count++;
return s->ret;
line_range_filter_init(&filter, ranges, line_fn, cb_data);
return line_range_filter_diff(&filter, one, two, xpp, xecfg);
}
static void pprint_rename(struct strbuf *name, const char *a, const char *b)
@@ -4087,51 +4197,15 @@ static void builtin_diff(const char *name_a,
xdi_diff_outf(&mf1, &mf2, NULL, quick_consume,
&ecbdata, &xpp, &xecfg);
} else if (line_ranges) {
struct line_range_callback lr_state;
unsigned int i;
long max_span = 0;
struct line_range_filter lr_filter;
memset(&lr_state, 0, sizeof(lr_state));
lr_state.orig_line_fn = fn_out_consume;
lr_state.orig_cb_data = &ecbdata;
lr_state.ranges = line_ranges;
strbuf_init(&lr_state.rhunk, 0);
strbuf_init(&lr_state.pending_rm, 0);
line_range_filter_init(&lr_filter, line_ranges,
fn_out_consume, &ecbdata);
/*
* Inflate ctxlen so that all changes within
* any single range are merged into one xdiff
* hunk and the inter-change context is emitted.
* The callback clips back to range boundaries.
*
* The optimal ctxlen depends on where changes
* fall within the range, which is only known
* after xdiff runs; the max range span is the
* upper bound that guarantees correctness in a
* single pass.
*/
for (i = 0; i < line_ranges->nr; i++) {
long span = line_ranges->ranges[i].end -
line_ranges->ranges[i].start;
if (span > max_span)
max_span = span;
}
if (max_span > xecfg.ctxlen)
xecfg.ctxlen = max_span;
if (xdi_diff_outf(&mf1, &mf2,
line_range_hunk_fn,
line_range_line_fn,
&lr_state, &xpp, &xecfg))
if (line_range_filter_diff(&lr_filter, &mf1, &mf2,
&xpp, &xecfg))
die("unable to generate diff for %s",
one->path);
flush_rhunk(&lr_state);
if (lr_state.ret)
die("unable to generate diff for %s",
one->path);
strbuf_release(&lr_state.rhunk);
strbuf_release(&lr_state.pending_rm);
} else if (xdi_diff_outf(&mf1, &mf2, NULL, fn_out_consume,
&ecbdata, &xpp, &xecfg))
die("unable to generate diff for %s", one->path);
@@ -4248,7 +4322,18 @@ static void builtin_diffstat(const char *name_a, const char *name_b,
xecfg.ctxlen = o->context;
xecfg.interhunkctxlen = o->interhunkcontext;
xecfg.flags = XDL_EMIT_NO_HUNK_HDR;
if (xdi_diff_outf(&mf1, &mf2, NULL,
if (p->line_ranges) {
struct line_range_filter lr_filter;
line_range_filter_init(&lr_filter, p->line_ranges,
diffstat_consume, diffstat);
if (line_range_filter_diff(&lr_filter, &mf1, &mf2,
&xpp, &xecfg))
die("unable to generate diffstat for %s",
one->path);
} else if (xdi_diff_outf(&mf1, &mf2, NULL,
diffstat_consume, diffstat, &xpp, &xecfg))
die("unable to generate diffstat for %s", one->path);
@@ -4278,11 +4363,29 @@ static void builtin_diffstat(const char *name_a, const char *name_b,
diff_free_filespec_data(two);
}
/*
* Is the 0-based line index within any of the tracked ranges?
* (range_set ranges are 0-based, half-open [start, end).) This is a
* one-shot query for a single line and scans; the streaming filter
* (line_range_line_fn) uses a forward cursor instead.
*/
static int idx_in_ranges(const struct range_set *ranges, long idx)
{
unsigned int i;
for (i = 0; i < ranges->nr; i++)
if (idx >= ranges->ranges[i].start &&
idx < ranges->ranges[i].end)
return 1;
return 0;
}
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)
struct diff_options *o,
const struct range_set *line_ranges)
{
mmfile_t mf1, mf2;
struct checkdiff_t data;
@@ -4322,7 +4425,19 @@ static void builtin_checkdiff(const char *name_a, const char *name_b,
memset(&xecfg, 0, sizeof(xecfg));
xecfg.ctxlen = 1; /* at least one context line */
xpp.flags = 0;
if (xdi_diff_outf(&mf1, &mf2, checkdiff_consume_hunk,
if (line_ranges) {
struct line_range_filter lr_filter;
line_range_filter_init(&lr_filter, line_ranges,
checkdiff_consume, &data);
lr_filter.orig_hunk_fn = checkdiff_consume_hunk;
if (line_range_filter_diff(&lr_filter, &mf1, &mf2,
&xpp, &xecfg))
die("unable to generate checkdiff for %s",
one->path);
} else if (xdi_diff_outf(&mf1, &mf2, checkdiff_consume_hunk,
checkdiff_consume, &data,
&xpp, &xecfg))
die("unable to generate checkdiff for %s", one->path);
@@ -4335,6 +4450,17 @@ static void builtin_checkdiff(const char *name_a, const char *name_b,
check_blank_at_eof(&mf1, &mf2, &ecbdata);
blank_at_eof = ecbdata.blank_at_eof_in_postimage;
/*
* check_blank_at_eof() scans the whole file; with -L,
* keep the report only when its line is in a tracked
* range. The error's location is the first trailing
* blank line (blank_at_eof, 1-based; ranges 0-based), so
* we scope by that line.
*/
if (blank_at_eof && line_ranges &&
!idx_in_ranges(line_ranges, blank_at_eof - 1))
blank_at_eof = 0;
if (blank_at_eof) {
static char *err;
if (!err)
@@ -5130,7 +5256,8 @@ static void run_checkdiff(struct diff_filepair *p, struct diff_options *o)
diff_fill_oid_info(p->one, o->repo->index);
diff_fill_oid_info(p->two, o->repo->index);
builtin_checkdiff(name, other, attr_path, p->one, p->two, o);
builtin_checkdiff(name, other, attr_path, p->one, p->two, o,
p->line_ranges);
}
void repo_diff_setup(struct repository *r, struct diff_options *options)