diff: extract a line-range diff helper for reuse

builtin_diff() open-codes the line-range filter setup and teardown around its xdi_diff_outf() call: zero the struct, point it at the output callback, inflate ctxlen to the largest range span so each range yields a single xdiff hunk, run the diff, flush the trailing range hunk, and release the buffer. The upcoming -L stat and check formats need the same sequence. Extract line_range_filter_init() for the setup and a line_range_filter_diff() helper that prepares the xdiff config the filter needs, runs an initialized filter through xdi_diff_outf(), flushes the final range hunk, and releases it, returning the latched error. The helper inflates ctxlen to the largest range span so each range yields a single xdiff hunk, and clears XDL_EMIT_NO_HUNK_HDR so the hunk headers the filter seeds its position from are always emitted. Folding both into the helper keeps these invariants, which the filter's position tracking relies on, in a single place for every consumer. builtin_diff() now does init + line_range_filter_diff(); the next two patches reuse them in builtin_diffstat() and builtin_checkdiff() instead of repeating the boilerplate. No behavior change: builtin_diff() leaves XDL_EMIT_NO_HUNK_HDR unset, so clearing it is a no-op until the suppressing consumers arrive. Signed-off-by: Michael Montalbo <mmontalbo@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Michael Montalbo committed Jun 27, 2026 at 17:28 UTC 56cf30f68c6ab06e34c295c62b081da8904b1c41
1 file changed +61 -39
diff.c
+61 -39
index 9751bb6798..6233a96bf0 100644 --- a/diff.c +++ b/diff.c @@ -2580,6 +2580,18 @@ static int quick_consume(void *priv, char *line UNUSED, unsigned long len UNUSED return 1; } +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) +{ + 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); +} + /* * 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: @@ -2744,6 +2756,50 @@ static int line_range_line_fn(void *priv, char *line, unsigned long len) 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; + + /* 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; +} + static void pprint_rename(struct strbuf *name, const char *a, const char *b) { const char *old_name = a; @@ -4108,49 +4164,15 @@ 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_filter 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.hunk.lines, 0); - - /* - * 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)) - die("unable to generate diff for %s", - one->path); + line_range_filter_init(&lr_filter, line_ranges, + fn_out_consume, &ecbdata); - flush_range_hunk(&lr_state); - if (lr_state.ret) + if (line_range_filter_diff(&lr_filter, &mf1, &mf2, + &xpp, &xecfg)) die("unable to generate diff for %s", one->path); - strbuf_release(&lr_state.hunk.lines); } else if (xdi_diff_outf(&mf1, &mf2, NULL, fn_out_consume, &ecbdata, &xpp, &xecfg)) die("unable to generate diff for %s", one->path);