From: Junio C Hamano Date: Tue, 29 Jan 2019 20:47:53 +0000 (-0800) Subject: Merge branch 'pw/diff-color-moved-ws-fix' X-Git-Tag: v2.21.0-rc0~70 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/15b07cba0b60f0fc5dea0be0d68a355a8161476d?hp=-c Merge branch 'pw/diff-color-moved-ws-fix' "git diff --color-moved-ws" updates. * pw/diff-color-moved-ws-fix: diff --color-moved-ws: handle blank lines diff --color-moved-ws: modify allow-indentation-change diff --color-moved-ws: optimize allow-indentation-change diff --color-moved=zebra: be stricter with color alternation diff --color-moved-ws: fix false positives diff --color-moved-ws: demonstrate false positives diff: allow --no-color-moved-ws Use "whitespace" consistently diff: document --no-color-moved --- 15b07cba0b60f0fc5dea0be0d68a355a8161476d diff --combined Documentation/diff-options.txt index b94d332f71,e1744fa80d..554a34080d --- a/Documentation/diff-options.txt +++ b/Documentation/diff-options.txt @@@ -293,8 -293,12 +293,12 @@@ dimmed-zebra: `dimmed_zebra` is a deprecated synonym. -- + --no-color-moved:: + Turn off move detection. This can be used to override configuration + settings. It is the same as `--color-moved=no`. + --color-moved-ws=:: - This configures how white spaces are ignored when performing the + This configures how whitespace is ignored when performing the move detection for `--color-moved`. ifdef::git-diff[] It can be set by the `diff.colorMovedWS` configuration setting. @@@ -302,6 -306,8 +306,8 @@@ endif::git-diff[ These modes can be given as a comma separated list: + -- + no:: + Do not ignore whitespace when performing move detection. ignore-space-at-eol:: Ignore changes in whitespace at EOL. ignore-space-change:: @@@ -312,12 -318,17 +318,17 @@@ ignore-all-space: Ignore whitespace when comparing lines. This ignores differences even if one line has whitespace where the other line has none. allow-indentation-change:: - Initially ignore any white spaces in the move detection, then + Initially ignore any whitespace in the move detection, then group the moved code blocks only into a block if the change in whitespace is the same per line. This is incompatible with the other modes. -- + --no-color-moved-ws:: + Do not ignore whitespace when performing move detection. This can be + used to override configuration settings. It is the same as + `--color-moved-ws=no`. + --word-diff[=]:: Show a word diff, using the to delimit changed words. By default, words are delimited by whitespace; see @@@ -524,8 -535,6 +535,8 @@@ struct), and want to know the history o came into being: use the feature iteratively to feed the interesting block in the preimage back into `-S`, and keep going until you get the very first version of the block. ++ +Binary files are searched as well. -G:: Look for differences whose patch text contains added/removed @@@ -545,9 -554,6 +556,9 @@@ While `git log -G"regexec\(regexp"` wil -S"regexec\(regexp" --pickaxe-regex` will not (because the number of occurrences of that string did not change). + +Unless `--text` is supplied patches of binary files without a textconv +filter will be ignored. ++ See the 'pickaxe' entry in linkgit:gitdiffcore[7] for more information. diff --combined diff.c index b96b7a4fc6,03ffe467e4..084bf54293 --- a/diff.c +++ b/diff.c @@@ -291,7 -291,7 +291,7 @@@ static int parse_color_moved(const cha return error(_("color moved setting must be one of 'no', 'default', 'blocks', 'zebra', 'dimmed-zebra', 'plain'")); } -static int parse_color_moved_ws(const char *arg) +static unsigned parse_color_moved_ws(const char *arg) { int ret = 0; struct string_list l = STRING_LIST_INIT_DUP; @@@ -304,7 -304,9 +304,9 @@@ strbuf_addstr(&sb, i->string); strbuf_trim(&sb); - if (!strcmp(sb.buf, "ignore-space-change")) + 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; @@@ -312,19 -314,15 +314,19 @@@ ret |= XDF_IGNORE_WHITESPACE; else if (!strcmp(sb.buf, "allow-indentation-change")) ret |= COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE; - else - error(_("ignoring unknown color-moved-ws mode '%s'"), sb.buf); + 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)) - die(_("color-moved-ws: allow-indentation-change cannot be combined with other whitespace modes")); + (ret & XDF_WHITESPACE_FLAGS)) { - error(_("color-moved-ws: allow-indentation-change cannot be combined with other white space modes")); ++ error(_("color-moved-ws: allow-indentation-change cannot be combined with other whitespace modes")); + ret |= COLOR_MOVED_WS_ERROR; + } string_list_clear(&l, 0); @@@ -345,8 -343,8 +347,8 @@@ int git_diff_ui_config(const char *var return 0; } if (!strcmp(var, "diff.colormovedws")) { - int cm = parse_color_moved_ws(value); - if (cm < 0) + unsigned cm = parse_color_moved_ws(value); + if (cm & COLOR_MOVED_WS_ERROR) return -1; diff_color_moved_ws_default = cm; return 0; @@@ -493,7 -491,7 +495,7 @@@ static const char *external_diff(void if (done_preparing) return external_diff_cmd; - external_diff_cmd = getenv("GIT_EXTERNAL_DIFF"); + external_diff_cmd = xstrdup_or_null(getenv("GIT_EXTERNAL_DIFF")); if (!external_diff_cmd) external_diff_cmd = external_diff_cmd_cfg; done_preparing = 1; @@@ -754,6 -752,8 +756,8 @@@ 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 */ enum diff_symbol s; }; #define EMITTED_DIFF_SYMBOL_INIT {NULL} @@@ -784,44 -784,85 +788,85 @@@ struct moved_entry struct moved_entry *next_line; }; - /** - * The struct ws_delta holds white space differences between moved lines, i.e. - * between '+' and '-' lines that have been detected to be a move. - * The string contains the difference in leading white spaces, before the - * rest of the line is compared using the white space config for move - * coloring. The current_longer indicates if the first string in the - * comparision is longer than the second. - */ - struct ws_delta { - char *string; - unsigned int current_longer : 1; - }; - #define WS_DELTA_INIT { NULL, 0 } - struct moved_block { struct moved_entry *match; - struct ws_delta wsd; + int wsd; /* The whitespace delta of this block */ }; static void moved_block_clear(struct moved_block *b) { - FREE_AND_NULL(b->wsd.string); - b->match = NULL; + memset(b, 0, sizeof(*b)); } - static int compute_ws_delta(const struct emitted_diff_symbol *a, - const struct emitted_diff_symbol *b, - struct ws_delta *out) + #define INDENT_BLANKLINE INT_MIN + + static void fill_es_indent_data(struct emitted_diff_symbol *es) { - const struct emitted_diff_symbol *longer = a->len > b->len ? a : b; - const struct emitted_diff_symbol *shorter = a->len > b->len ? b : a; - int d = longer->len - shorter->len; + 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 (strncmp(longer->line + d, shorter->line, shorter->len)) + 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 *out) + { + int a_len = a->len, + b_len = b->len, + a_off = a->indent_off, + a_width = a->indent_width, + b_off = b->indent_off, + b_width = b->indent_width; + int delta; + + if (a_width == INDENT_BLANKLINE && b_width == INDENT_BLANKLINE) { + *out = INDENT_BLANKLINE; + return 1; + } + + if (a->s == DIFF_SYMBOL_PLUS) + delta = a_width - b_width; + else + delta = b_width - a_width; + + if (a_len - a_off != b_len - b_off || + memcmp(a->line + a_off, b->line + b_off, a_len - a_off)) return 0; - out->string = xmemdupz(longer->line, d); - out->current_longer = (a == longer); + *out = delta; return 1; } @@@ -833,51 -874,53 +878,53 @@@ static int cmp_in_block_with_wsd(const int n) { struct emitted_diff_symbol *l = &o->emitted_symbols->buf[n]; - int al = cur->es->len, cl = l->len; + int al = cur->es->len, bl = match->es->len, cl = l->len; const char *a = cur->es->line, *b = match->es->line, *c = l->line; - - int wslen; + int a_off = cur->es->indent_off, + a_width = cur->es->indent_width, + c_off = l->indent_off, + c_width = l->indent_width; + int delta; /* - * We need to check if 'cur' is equal to 'match'. - * As those are from the same (+/-) side, we do not need to adjust for - * indent changes. However these were found using fuzzy matching - * so we do have to check if they are equal. + * We need to check if 'cur' is equal to 'match'. As those + * are from the same (+/-) side, we do not need to adjust for + * indent changes. However these were found using fuzzy + * matching so we do have to check if they are equal. Here we + * just check the lengths. We delay calling memcmp() to check + * the contents until later as if the length comparison for a + * and c fails we can avoid the call all together. */ - if (strcmp(a, b)) + if (al != bl) return 1; - if (!pmb->wsd.string) - /* - * The white space delta is not active? This can happen - * when we exit early in this function. - */ - return 1; + /* If 'l' and 'cur' are both blank then they match. */ + if (a_width == INDENT_BLANKLINE && c_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 are still the same as before. - * - * To do so we need to compare 'l' to 'cur', adjusting the - * one of them for the white spaces, depending which was longer. + * 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 and that the text of 'l' and 'cur' + * after the indentation match. */ + if (cur->es->s == DIFF_SYMBOL_PLUS) + delta = a_width - c_width; + else + delta = c_width - a_width; - wslen = strlen(pmb->wsd.string); - if (pmb->wsd.current_longer) { - c += wslen; - cl -= wslen; - } else { - a += wslen; - al -= wslen; - } - - if (al != cl || memcmp(a, c, al)) - return 1; + /* + * If the previous lines of this block were all blank then set its + * whitespace delta. + */ + if (pmb->wsd == INDENT_BLANKLINE) + pmb->wsd = delta; - return 0; + return !(delta == pmb->wsd && al - a_off == cl - c_off && + !memcmp(a, b, al) && ! + memcmp(a + a_off, c + c_off, al - a_off)); } static int moved_entry_cmp(const void *hashmap_cmp_fn_data, @@@ -943,6 -986,9 +990,9 @@@ static void add_lines_to_move_detection continue; } + if (o->color_moved_ws_handling & + COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE) + fill_es_indent_data(&o->emitted_symbols->buf[n]); key = prepare_entry(o, n); if (prev_line && prev_line->es->s == o->emitted_symbols->buf[n].s) prev_line->next_line = key; @@@ -1021,8 -1067,7 +1071,7 @@@ static int shrink_potential_moved_block if (lp < pmb_nr && rp > -1 && lp < rp) { pmb[lp] = pmb[rp]; - pmb[rp].match = NULL; - pmb[rp].wsd.string = NULL; + memset(&pmb[rp], 0, sizeof(pmb[rp])); rp--; lp++; } @@@ -1042,14 -1087,17 +1091,17 @@@ * 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. */ - static void adjust_last_block(struct diff_options *o, int n, int block_length) + 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; + return block_length; for (i = 1; i < block_length + 1; i++) { const char *c = o->emitted_symbols->buf[n - i].line; for (; *c; c++) { @@@ -1057,11 -1105,12 +1109,12 @@@ continue; alnum_count++; if (alnum_count >= COLOR_MOVED_MIN_ALNUM_COUNT) - return; + return 1; } } for (i = 1; i < block_length + 1; i++) o->emitted_symbols->buf[n - i].flags &= ~DIFF_SYMBOL_MOVED_LINE; + return 0; } /* Find blocks of moved code, delegate actual coloring decision to helper */ @@@ -1071,7 -1120,7 +1124,7 @@@ static void mark_color_as_moved(struct { struct moved_block *pmb = NULL; /* potentially moved blocks */ int pmb_nr = 0, pmb_alloc = 0; - int n, flipped_block = 1, block_length = 0; + int n, flipped_block = 0, block_length = 0; for (n = 0; n < o->emitted_symbols->nr; n++) { @@@ -1079,6 -1128,7 +1132,7 @@@ struct moved_entry *key; struct moved_entry *match = NULL; struct emitted_diff_symbol *l = &o->emitted_symbols->buf[n]; + enum diff_symbol last_symbol = 0; switch (l->s) { case DIFF_SYMBOL_PLUS: @@@ -1094,7 -1144,7 +1148,7 @@@ free(key); break; default: - flipped_block = 1; + flipped_block = 0; } if (!match) { @@@ -1105,13 -1155,16 +1159,16 @@@ moved_block_clear(&pmb[i]); pmb_nr = 0; block_length = 0; + flipped_block = 0; + last_symbol = l->s; continue; } - l->flags |= DIFF_SYMBOL_MOVED_LINE; - - if (o->color_moved == COLOR_MOVED_PLAIN) + if (o->color_moved == COLOR_MOVED_PLAIN) { + last_symbol = l->s; + l->flags |= DIFF_SYMBOL_MOVED_LINE; continue; + } if (o->color_moved_ws_handling & COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE) @@@ -1134,21 -1187,27 +1191,27 @@@ &pmb[pmb_nr].wsd)) pmb[pmb_nr++].match = match; } else { - pmb[pmb_nr].wsd.string = NULL; + pmb[pmb_nr].wsd = 0; pmb[pmb_nr++].match = match; } } - flipped_block = (flipped_block + 1) % 2; + if (adjust_last_block(o, n, block_length) && + pmb_nr && last_symbol != l->s) + flipped_block = (flipped_block + 1) % 2; + else + flipped_block = 0; - adjust_last_block(o, n, block_length); block_length = 0; } - block_length++; - - if (flipped_block && o->color_moved != COLOR_MOVED_BLOCKS) - l->flags |= DIFF_SYMBOL_MOVED_LINE_ALT; + 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; + } + last_symbol = l->s; } adjust_last_block(o, n, block_length); @@@ -1492,7 -1551,7 +1555,7 @@@ static void emit_diff_symbol_from_struc 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, len, flags, s}; + struct emitted_diff_symbol e = {line, len, flags, 0, 0, s}; if (o->emitted_symbols) append_emitted_diff_symbol(o, &e); @@@ -1641,8 -1700,7 +1704,8 @@@ static void emit_hunk_header(struct emi strbuf_release(&msgbuf); } -static struct diff_tempfile *claim_diff_tempfile(void) { +static struct diff_tempfile *claim_diff_tempfile(void) +{ int i; for (i = 0; i < ARRAY_SIZE(diff_temp); i++) if (!diff_temp[i].name) @@@ -3318,14 -3376,14 +3381,14 @@@ void diff_set_mnemonic_prefix(struct di options->b_prefix = b; } -struct userdiff_driver *get_textconv(struct index_state *istate, +struct userdiff_driver *get_textconv(struct repository *r, struct diff_filespec *one) { if (!DIFF_FILE_VALID(one)) return NULL; - diff_filespec_load_driver(one, istate); - return userdiff_get_textconv(one->driver); + diff_filespec_load_driver(one, r->index); + return userdiff_get_textconv(r, one->driver); } static void builtin_diff(const char *name_a, @@@ -3374,8 -3432,8 +3437,8 @@@ } if (o->flags.allow_textconv) { - textconv_one = get_textconv(o->repo->index, one); - textconv_two = get_textconv(o->repo->index, two); + textconv_one = get_textconv(o->repo, one); + textconv_two = get_textconv(o->repo, two); } /* Never use a non-valid filename anywhere if at all possible */ @@@ -4824,8 -4882,7 +4887,8 @@@ static int parse_diff_filter_opt(const return 0; } -static void enable_patch_output(int *fmt) { +static void enable_patch_output(int *fmt) +{ *fmt &= ~DIFF_FORMAT_NO_OUTPUT; *fmt |= DIFF_FORMAT_PATCH; } @@@ -5040,13 -5097,12 +5103,15 @@@ int diff_opt_parse(struct diff_options else if (skip_prefix(arg, "--color-moved=", &arg)) { int cm = parse_color_moved(arg); if (cm < 0) - die("bad --color-moved argument: %s", arg); + return error("bad --color-moved argument: %s", arg); options->color_moved = cm; + } else if (!strcmp(arg, "--no-color-moved-ws")) { + options->color_moved_ws_handling = 0; } else if (skip_prefix(arg, "--color-moved-ws=", &arg)) { - options->color_moved_ws_handling = parse_color_moved_ws(arg); + unsigned cm = parse_color_moved_ws(arg); + if (cm & COLOR_MOVED_WS_ERROR) + return -1; + options->color_moved_ws_handling = cm; } else if (skip_to_optional_arg_default(arg, "--color-words", &options->word_regex, NULL)) { options->use_color = 1; options->word_diff = DIFF_WORDS_COLOR; @@@ -6443,7 -6499,7 +6508,7 @@@ int textconv_object(struct repository * df = alloc_filespec(path); fill_filespec(df, oid, oid_valid, mode); - textconv = get_textconv(r->index, df); + textconv = get_textconv(r, df); if (!textconv) { free_filespec(df); return 0; diff --combined t/t4015-diff-whitespace.sh index 9a3e4fdfec,9d6f88b07f..ab4670d236 --- a/t/t4015-diff-whitespace.sh +++ b/t/t4015-diff-whitespace.sh @@@ -1802,8 -1802,8 +1802,8 @@@ test_expect_success 'only move detectio -a long line to exceed per-line minimum -another long line to exceed per-line minimum -original file - +Qa long line to exceed per-line minimum - +Qanother long line to exceed per-line minimum + +Qa long line to exceed per-line minimum + +Qanother long line to exceed per-line minimum +new file EOF test_cmp expected actual @@@ -1827,6 -1827,7 +1827,7 @@@ test_expect_success 'compare whitespac QQQthat has similar lines QQQto previous blocks, but with different indent QQQYetQAnotherQoutlierQ + QLine with internal w h i t e s p a c e change EOF git add text.txt && @@@ -1847,6 -1848,7 +1848,7 @@@ QQthat has similar lines QQto previous blocks, but with different indent QQYetQAnotherQoutlier + QLine with internal whitespace change EOF git diff --color --color-moved --color-moved-ws=allow-indentation-change >actual.raw && @@@ -1856,7 -1858,7 +1858,7 @@@ diff --git a/text.txt b/text.txt --- a/text.txt +++ b/text.txt - @@ -1,14 +1,14 @@ + @@ -1,15 +1,15 @@ -QIndented -QText across -Qsome lines @@@ -1871,6 -1873,7 +1873,7 @@@ -QQQthat has similar lines -QQQto previous blocks, but with different indent -QQQYetQAnotherQoutlierQ + -QLine with internal w h i t e s p a c e change +QQIndented +QQText across +QQsome lines @@@ -1885,29 -1888,12 +1888,30 @@@ +QQthat has similar lines +QQto previous blocks, but with different indent +QQYetQAnotherQoutlier + +QLine with internal whitespace change EOF test_cmp expected actual ' +test_expect_success 'bogus settings in move detection erroring out' ' + test_must_fail git diff --color-moved=bogus 2>err && + test_i18ngrep "must be one of" err && + test_i18ngrep bogus err && + + test_must_fail git -c diff.colormoved=bogus diff 2>err && + test_i18ngrep "must be one of" err && + test_i18ngrep "from command-line config" err && + + test_must_fail git diff --color-moved-ws=bogus 2>err && + test_i18ngrep "possible values" err && + test_i18ngrep bogus err && + + test_must_fail git -c diff.colormovedws=bogus diff 2>err && + test_i18ngrep "possible values" err && + test_i18ngrep "from command-line config" err +' + test_expect_success 'compare whitespace delta incompatible with other space options' ' test_must_fail git diff \ --color-moved-ws=allow-indentation-change,ignore-all-space \ @@@ -1915,4 -1901,93 +1919,93 @@@ test_i18ngrep allow-indentation-change err ' + EMPTY='' + test_expect_success 'compare mixed whitespace delta across moved blocks' ' + + git reset --hard && + tr Q_ "\t " <<-EOF >text.txt && + ${EMPTY} + ____too short without + ${EMPTY} + ___being grouped across blank line + ${EMPTY} + context + lines + to + anchor + ____Indented text to + _Q____be further indented by four spaces across + ____Qseveral lines + QQ____These two lines have had their + ____indentation reduced by four spaces + Qdifferent indentation change + ____too short + EOF + + git add text.txt && + git commit -m "add text.txt" && + + tr Q_ "\t " <<-EOF >text.txt && + context + lines + to + anchor + QIndented text to + QQbe further indented by four spaces across + Q____several lines + ${EMPTY} + QQtoo short without + ${EMPTY} + Q_______being grouped across blank line + ${EMPTY} + Q_QThese two lines have had their + indentation reduced by four spaces + QQdifferent indentation change + __Qtoo short + EOF + + git -c color.diff.whitespace="normal red" \ + -c core.whitespace=space-before-tab \ + diff --color --color-moved --ws-error-highlight=all \ + --color-moved-ws=allow-indentation-change >actual.raw && + grep -v "index" actual.raw | test_decode_color >actual && + + cat <<-\EOF >expected && + diff --git a/text.txt b/text.txt + --- a/text.txt + +++ b/text.txt + @@ -1,16 +1,16 @@ + - + - too short without + - + - being grouped across blank line + - + context + lines + to + anchor + - Indented text to + - be further indented by four spaces across + - several lines + - These two lines have had their + - indentation reduced by four spaces + - different indentation change + - too short + + Indented text to + + be further indented by four spaces across + + several lines + + + + too short without + + + + being grouped across blank line + + + + These two lines have had their + +indentation reduced by four spaces + + different indentation change + + too short + EOF + + test_cmp expected actual + ' + test_done