From d9c66f0b5bfdf3fc2898b7baad1bb9a72bfd7bf7 Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Mon, 13 Aug 2018 04:33:04 -0700 Subject: range-diff: first rudimentary implementation At this stage, `git range-diff` can determine corresponding commits of two related commit ranges. This makes use of the recently introduced implementation of the linear assignment algorithm. The core of this patch is a straight port of the ideas of tbdiff, the apparently dormant project at https://github.com/trast/tbdiff. The output does not at all match `tbdiff`'s output yet, as this patch really concentrates on getting the patch matching part right. Note: due to differences in the diff algorithm (`tbdiff` uses the Python module `difflib`, Git uses its xdiff fork), the cost matrix calculated by `range-diff` is different (but very similar) to the one calculated by `tbdiff`. Therefore, it is possible that they find different matching commits in corner cases (e.g. when a patch was split into two patches of roughly equal length). Signed-off-by: Johannes Schindelin Signed-off-by: Junio C Hamano --- range-diff.h | 7 +++++++ 1 file changed, 7 insertions(+) create mode 100644 range-diff.h (limited to 'range-diff.h') diff --git a/range-diff.h b/range-diff.h new file mode 100644 index 0000000000..7b6eef303f --- /dev/null +++ b/range-diff.h @@ -0,0 +1,7 @@ +#ifndef RANGE_DIFF_H +#define RANGE_DIFF_H + +int show_range_diff(const char *range1, const char *range2, + int creation_factor); + +#endif -- cgit v1.3 From c8c5e43ac3f9a5b785faf16f10bb8e2c493606a4 Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Mon, 13 Aug 2018 04:33:07 -0700 Subject: range-diff: also show the diff between patches Just like tbdiff, we now show the diff between matching patches. This is a "diff of two diffs", so it can be a bit daunting to read for the beginner. An alternative would be to display an interdiff, i.e. the hypothetical diff which is the result of first reverting the old diff and then applying the new diff. Especially when rebasing frequently, an interdiff is often not feasible, though: if the old diff cannot be applied in reverse (due to a moving upstream), an interdiff can simply not be inferred. This commit brings `range-diff` closer to feature parity with regard to tbdiff. To make `git range-diff` respect e.g. color.diff.* settings, we have to adjust git_branch_config() accordingly. Note: while we now parse diff options such as --color, the effect is not yet the same as in tbdiff, where also the commit pairs would be colored. This is left for a later commit. Note also: while tbdiff accepts the `--no-patches` option to suppress these diffs between patches, we prefer the `-s` (or `--no-patch`) option that is automatically supported via our use of diff_opt_parse(). And finally note: to support diff options, we have to call `parse_options()` such that it keeps unknown options, and then loop over those and let `diff_opt_parse()` handle them. After that loop, we have to call `parse_options()` again, to make sure that no unknown options are left. Helped-by: Thomas Gummerer Helped-by: Eric Sunshine Signed-off-by: Johannes Schindelin Signed-off-by: Junio C Hamano --- builtin/range-diff.c | 31 +++++++++++++++++++++++++++++-- range-diff.c | 34 +++++++++++++++++++++++++++++++--- range-diff.h | 4 +++- 3 files changed, 63 insertions(+), 6 deletions(-) (limited to 'range-diff.h') diff --git a/builtin/range-diff.c b/builtin/range-diff.c index 94c1f362cc..3b06ed9449 100644 --- a/builtin/range-diff.c +++ b/builtin/range-diff.c @@ -2,6 +2,7 @@ #include "builtin.h" #include "parse-options.h" #include "range-diff.h" +#include "config.h" static const char * const builtin_range_diff_usage[] = { N_("git range-diff [] .. .."), @@ -13,15 +14,40 @@ NULL int cmd_range_diff(int argc, const char **argv, const char *prefix) { int creation_factor = 60; + struct diff_options diffopt = { NULL }; struct option options[] = { OPT_INTEGER(0, "creation-factor", &creation_factor, N_("Percentage by which creation is weighted")), OPT_END() }; - int res = 0; + int i, j, res = 0; struct strbuf range1 = STRBUF_INIT, range2 = STRBUF_INIT; + git_config(git_diff_ui_config, NULL); + + diff_setup(&diffopt); + diffopt.output_format = DIFF_FORMAT_PATCH; + argc = parse_options(argc, argv, NULL, options, + builtin_range_diff_usage, PARSE_OPT_KEEP_UNKNOWN | + PARSE_OPT_KEEP_DASHDASH | PARSE_OPT_KEEP_ARGV0); + + for (i = j = 1; i < argc && strcmp("--", argv[i]); ) { + int c = diff_opt_parse(&diffopt, argv + i, argc - i, prefix); + + if (!c) + argv[j++] = argv[i++]; + else + i += c; + } + while (i < argc) + argv[j++] = argv[i++]; + argc = j; + diff_setup_done(&diffopt); + + /* Make sure that there are no unparsed options */ + argc = parse_options(argc, argv, NULL, + options + ARRAY_SIZE(options) - 1, /* OPT_END */ builtin_range_diff_usage, 0); if (argc == 2) { @@ -59,7 +85,8 @@ int cmd_range_diff(int argc, const char **argv, const char *prefix) usage_with_options(builtin_range_diff_usage, options); } - res = show_range_diff(range1.buf, range2.buf, creation_factor); + res = show_range_diff(range1.buf, range2.buf, creation_factor, + &diffopt); strbuf_release(&range1); strbuf_release(&range2); diff --git a/range-diff.c b/range-diff.c index 2d94200d30..71883a4b7d 100644 --- a/range-diff.c +++ b/range-diff.c @@ -6,6 +6,7 @@ #include "hashmap.h" #include "xdiff-interface.h" #include "linear-assignment.h" +#include "diffcore.h" struct patch_util { /* For the search for an exact match */ @@ -258,7 +259,31 @@ static const char *short_oid(struct patch_util *util) return find_unique_abbrev(&util->oid, DEFAULT_ABBREV); } -static void output(struct string_list *a, struct string_list *b) +static struct diff_filespec *get_filespec(const char *name, const char *p) +{ + struct diff_filespec *spec = alloc_filespec(name); + + fill_filespec(spec, &null_oid, 0, 0644); + spec->data = (char *)p; + spec->size = strlen(p); + spec->should_munmap = 0; + spec->is_stdin = 1; + + return spec; +} + +static void patch_diff(const char *a, const char *b, + struct diff_options *diffopt) +{ + diff_queue(&diff_queued_diff, + get_filespec("a", a), get_filespec("b", b)); + + diffcore_std(diffopt); + diff_flush(diffopt); +} + +static void output(struct string_list *a, struct string_list *b, + struct diff_options *diffopt) { int i = 0, j = 0; @@ -300,6 +325,9 @@ static void output(struct string_list *a, struct string_list *b) printf("%d: %s ! %d: %s\n", b_util->matching + 1, short_oid(a_util), j + 1, short_oid(b_util)); + if (!(diffopt->output_format & DIFF_FORMAT_NO_OUTPUT)) + patch_diff(a->items[b_util->matching].string, + b->items[j].string, diffopt); a_util->shown = 1; j++; } @@ -307,7 +335,7 @@ static void output(struct string_list *a, struct string_list *b) } int show_range_diff(const char *range1, const char *range2, - int creation_factor) + int creation_factor, struct diff_options *diffopt) { int res = 0; @@ -322,7 +350,7 @@ int show_range_diff(const char *range1, const char *range2, if (!res) { find_exact_matches(&branch1, &branch2); get_correspondences(&branch1, &branch2, creation_factor); - output(&branch1, &branch2); + output(&branch1, &branch2, diffopt); } string_list_clear(&branch1, 1); diff --git a/range-diff.h b/range-diff.h index 7b6eef303f..2407d46a30 100644 --- a/range-diff.h +++ b/range-diff.h @@ -1,7 +1,9 @@ #ifndef RANGE_DIFF_H #define RANGE_DIFF_H +#include "diff.h" + int show_range_diff(const char *range1, const char *range2, - int creation_factor); + int creation_factor, struct diff_options *diffopt); #endif -- cgit v1.3