/* * 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 "userdiff.h" #include "submodule-config.h" #include "submodule.h" #include "ll-merge.h" #include "string-list.h" #include "argv-array.h" #include "graph.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 = 400; static int diff_suppress_blank_empty; static int diff_use_color_default = -1; 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_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 */ }; static NORETURN void die_want_option(const char *option_name) { die(_("option '%s' requires a value"), option_name); } static int parse_diff_color_slot(const char *var) { if (!strcasecmp(var, "context") || !strcasecmp(var, "plain")) return DIFF_CONTEXT; if (!strcasecmp(var, "meta")) return DIFF_METAINFO; if (!strcasecmp(var, "frag")) return DIFF_FRAGINFO; if (!strcasecmp(var, "old")) return DIFF_FILE_OLD; if (!strcasecmp(var, "new")) return DIFF_FILE_NEW; if (!strcasecmp(var, "commit")) return DIFF_COMMIT; if (!strcasecmp(var, "whitespace")) return DIFF_WHITESPACE; if (!strcasecmp(var, "func")) return DIFF_FUNCINFO; return -1; } 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(¶ms, params_copy, ',', -1); for (i = 0; i < params.nr; i++) { const char *p = params.items[i].string; if (!strcmp(p, "changes")) { DIFF_OPT_CLR(options, DIRSTAT_BY_LINE); DIFF_OPT_CLR(options, DIRSTAT_BY_FILE); } else if (!strcmp(p, "lines")) { DIFF_OPT_SET(options, DIRSTAT_BY_LINE); DIFF_OPT_CLR(options, DIRSTAT_BY_FILE); } else if (!strcmp(p, "files")) { DIFF_OPT_CLR(options, DIRSTAT_BY_LINE); DIFF_OPT_SET(options, DIRSTAT_BY_FILE); } else if (!strcmp(p, "noncumulative")) { DIFF_OPT_CLR(options, DIRSTAT_CUMULATIVE); } else if (!strcmp(p, "cumulative")) { DIFF_OPT_SET(options, DIRSTAT_CUMULATIVE); } 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(¶ms, 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; else return -1; return 0; } static 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; 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 = 1; } int git_diff_heuristic_config(const char *var, const char *value, void *cb) { if (!strcmp(var, "diff.indentheuristic")) diff_indent_heuristic = git_config_bool(var, value); return 0; } 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.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.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 (!strcmp(var, "diff.wserrorhighlight")) { int val = parse_ws_error_highlight(value); if (val < 0) return -1; ws_error_highlight_default = val; return 0; } 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]); } /* 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 (starts_with(var, "submodule.")) return parse_submodule_config_option(var, value); 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, 1); int need_two = quote_c_style(two, NULL, NULL, 1); struct strbuf res = STRBUF_INIT; if (need_one + need_two) { strbuf_addch(&res, '"'); quote_c_style(one, &res, NULL, 1); quote_c_style(two, &res, NULL, 1); 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 = 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]; typedef unsigned long (*sane_truncate_fn)(char *line, unsigned long len); 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; sane_truncate_fn truncate; 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(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(one, 0)) 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 diff_filespec *one) { if (!DIFF_FILE_VALID(one)) return 0; diff_populate_filespec(one, CHECK_SIZE_ONLY); return one->size; } static int count_trailing_blank(mmfile_t *mf, unsigned ws_rule) { 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, ws_rule)) 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; unsigned ws_rule = ecbdata->ws_rule; l1 = count_trailing_blank(mf1, ws_rule); l2 = count_trailing_blank(mf2, ws_rule); 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, const char *reset, int first, const char *line, int len) { int has_trailing_newline, has_trailing_carriage_return; int nofirst; FILE *file = o->file; fputs(diff_line_prefix(o), file); if (len == 0) { has_trailing_newline = (first == '\n'); has_trailing_carriage_return = (!has_trailing_newline && (first == '\r')); nofirst = has_trailing_newline || has_trailing_carriage_return; } else { 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--; nofirst = 0; } if (len || !nofirst) { fputs(set, file); if (!nofirst) fputc(first, file); fwrite(line, len, 1, file); 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, reset, line[0], line+1, len-1); } 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, ecbdata->ws_rule); } static void emit_line_checked(const char *reset, struct emit_callback *ecbdata, const char *line, int len, enum color_diff color, unsigned ws_error_highlight, char sign) { const char *set = diff_get_color(ecbdata->color_diff, color); const char *ws = NULL; if (ecbdata->opt->ws_error_highlight & ws_error_highlight) { ws = diff_get_color(ecbdata->color_diff, DIFF_WHITESPACE); if (!*ws) ws = NULL; } if (!ws) emit_line_0(ecbdata->opt, set, reset, sign, line, len); else if (sign == '+' && new_blank_line_at_eof(ecbdata, line, len)) /* Blank line at EOF - paint '+' as well */ emit_line_0(ecbdata->opt, ws, reset, sign, line, len); else { /* Emit just the prefix, then the rest. */ emit_line_0(ecbdata->opt, set, reset, sign, "", 0); ws_check_emit(line, len, ecbdata->ws_rule, ecbdata->opt->file, set, reset, ws); } } static void emit_add_line(const char *reset, struct emit_callback *ecbdata, const char *line, int len) { emit_line_checked(reset, ecbdata, line, len, DIFF_FILE_NEW, WSEH_NEW, '+'); } static void emit_del_line(const char *reset, struct emit_callback *ecbdata, const char *line, int len) { emit_line_checked(reset, ecbdata, line, len, DIFF_FILE_OLD, WSEH_OLD, '-'); } static void emit_context_line(const char *reset, struct emit_callback *ecbdata, const char *line, int len) { emit_line_checked(reset, ecbdata, line, len, DIFF_CONTEXT, WSEH_CONTEXT, ' '); } 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); 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 "@@ -, + @@", * it always is at least 10 bytes long. */ if (len < 10 || memcmp(line, atat, 2) || !(ep = memmem(line + 2, len - 2, atat, 2))) { emit_line(ecbdata->opt, context, reset, line, len); return; } ep += 2; /* skip over @@ */ /* The hunk header in fraginfo color */ strbuf_addstr(&msgbuf, frag); 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); emit_line(ecbdata->opt, "", "", msgbuf.buf, msgbuf.len); 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; die("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 print_line_count(FILE *file, int count) { switch (count) { case 0: fprintf(file, "0,0"); break; case 1: fprintf(file, "1"); break; default: fprintf(file, "1,%d", count); break; } } static void emit_rewrite_lines(struct emit_callback *ecb, int prefix, const char *data, int size) { const char *endp = NULL; static const char *nneof = " No newline at end of file\n"; const char *reset = diff_get_color(ecb->color_diff, DIFF_RESET); 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(reset, ecb, data, len); } else { ecb->lno_in_postimage++; emit_add_line(reset, ecb, data, len); } size -= len; data += len; } if (!endp) { const char *context = diff_get_color(ecb->color_diff, DIFF_CONTEXT); putc('\n', ecb->opt->file); emit_line_0(ecb->opt, context, reset, '\\', nneof, strlen(nneof)); } } 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; const char *name_a_tab, *name_b_tab; const char *metainfo = diff_get_color(o->use_color, DIFF_METAINFO); const char *fraginfo = diff_get_color(o->use_color, DIFF_FRAGINFO); const char *reset = diff_get_color(o->use_color, DIFF_RESET); 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; const char *line_prefix = diff_line_prefix(o); if (diff_mnemonic_prefix && DIFF_OPT_TST(o, 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 == '/'); name_a_tab = strchr(name_a, ' ') ? "\t" : ""; name_b_tab = strchr(name_b, ' ') ? "\t" : ""; 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(textconv_one, one, &data_one); size_two = fill_textconv(textconv_two, two, &data_two); memset(&ecbdata, 0, sizeof(ecbdata)); ecbdata.color_diff = want_color(o->use_color); ecbdata.ws_rule = whitespace_rule(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); fprintf(o->file, "%s%s--- %s%s%s\n%s%s+++ %s%s%s\n%s%s@@ -", line_prefix, metainfo, a_name.buf, name_a_tab, reset, line_prefix, metainfo, b_name.buf, name_b_tab, reset, line_prefix, fraginfo); if (!o->irreversible_delete) print_line_count(o->file, lc_a); else fprintf(o->file, "?,?"); fprintf(o->file, " +"); print_line_count(o->file, lc_b); fprintf(o->file, " @@%s\n", reset); 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; 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, old, 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(FILE *fp, struct diff_words_style_elem *st_el, const char *newline, size_t count, const char *buf, const char *line_prefix) { int print = 0; while (count) { char *p = memchr(buf, '\n', count); if (print) fputs(line_prefix, fp); if (p != buf) { if (st_el->color && fputs(st_el->color, fp) < 0) return -1; if (fputs(st_el->prefix, fp) < 0 || fwrite(buf, p ? p - buf : count, 1, fp) != 1 || fputs(st_el->suffix, fp) < 0) return -1; if (st_el->color && *st_el->color && fputs(GIT_COLOR_RESET, fp) < 0) return -1; } if (!p) return 0; if (fputs(newline, fp) < 0) return -1; count -= p + 1 - buf; buf = p + 1; print = 1; } 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, char *line, unsigned long len) { struct diff_words_data *diff_words = priv; struct diff_words_style *style = diff_words->style; int minus_first, minus_len, plus_first, plus_len; const char *minus_begin, *minus_end, *plus_begin, *plus_end; struct diff_options *opt = diff_words->opt; const char *line_prefix; if (line[0] != '@' || parse_hunk_header(line, len, &minus_first, &minus_len, &plus_first, &plus_len)) return; 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->file, &style->ctx, style->newline, plus_begin - diff_words->current_plus, diff_words->current_plus, line_prefix); if (*(plus_begin - 1) == '\n') fputs(line_prefix, diff_words->opt->file); } if (minus_begin != minus_end) { fn_out_diff_words_write_helper(diff_words->opt->file, &style->old, style->newline, minus_end - minus_begin, minus_begin, line_prefix); } if (plus_begin != plus_end) { fn_out_diff_words_write_helper(diff_words->opt->file, &style->new, style->newline, plus_end - plus_begin, plus_begin, line_prefix); } 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) { if (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; return *begin >= *end; } 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) { fputs(line_prefix, diff_words->opt->file); fn_out_diff_words_write_helper(diff_words->opt->file, &style->old, style->newline, diff_words->minus.text.size, diff_words->minus.text.ptr, line_prefix); 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, 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)) fputs(line_prefix, diff_words->opt->file); fn_out_diff_words_write_helper(diff_words->opt->file, &style->ctx, style->newline, diff_words->plus.text.ptr + diff_words->plus.text.size - diff_words->current_plus, diff_words->current_plus, line_prefix); } 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) { if (ecbdata->diff_words->minus.text.size || ecbdata->diff_words->plus.text.size) diff_words_show(ecbdata->diff_words); } static void diff_filespec_load_driver(struct diff_filespec *one) { /* Use already-loaded driver */ if (one->driver) return; if (S_ISREG(one->mode)) one->driver = userdiff_find_by_path(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) { diff_filespec_load_driver(one); 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)); ecbdata->diff_words = xcalloc(1, sizeof(struct diff_words_data)); ecbdata->diff_words->type = o->word_diff; ecbdata->diff_words->opt = o; if (!o->word_regex) o->word_regex = userdiff_word_regex(one); if (!o->word_regex) o->word_regex = userdiff_word_regex(two); 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.color = diff_get_color_opt(o, DIFF_FILE_OLD); st->new.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 (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(struct emit_callback *ecb, char *line, unsigned long len) { const char *cp; unsigned long allot; size_t l = len; if (ecb->truncate) return ecb->truncate(line, 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 void fn_out_consume(void *priv, char *line, unsigned long len) { struct emit_callback *ecbdata = priv; const char *meta = diff_get_color(ecbdata->color_diff, DIFF_METAINFO); const char *context = diff_get_color(ecbdata->color_diff, DIFF_CONTEXT); const char *reset = diff_get_color(ecbdata->color_diff, DIFF_RESET); struct diff_options *o = ecbdata->opt; const char *line_prefix = diff_line_prefix(o); o->found_changes = 1; if (ecbdata->header) { fprintf(o->file, "%s", ecbdata->header->buf); strbuf_reset(ecbdata->header); ecbdata->header = NULL; } if (ecbdata->label_path[0]) { const char *name_a_tab, *name_b_tab; name_a_tab = strchr(ecbdata->label_path[0], ' ') ? "\t" : ""; name_b_tab = strchr(ecbdata->label_path[1], ' ') ? "\t" : ""; fprintf(o->file, "%s%s--- %s%s%s\n", line_prefix, meta, ecbdata->label_path[0], reset, name_a_tab); fprintf(o->file, "%s%s+++ %s%s%s\n", line_prefix, meta, ecbdata->label_path[1], reset, name_b_tab); 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(ecbdata, line, len); find_lno(line, ecbdata); emit_hunk_header(ecbdata, line, len); if (line[len-1] != '\n') putc('\n', o->file); return; } if (ecbdata->diff_words) { if (line[0] == '-') { diff_words_append(line, len, &ecbdata->diff_words->minus); return; } else if (line[0] == '+') { diff_words_append(line, len, &ecbdata->diff_words->plus); return; } 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; } diff_words_flush(ecbdata); if (ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN) { emit_line(o, context, reset, line, len); fputs("~\n", o->file); } else { /* * 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); } return; } switch (line[0]) { case '+': ecbdata->lno_in_postimage++; emit_add_line(reset, ecbdata, line + 1, len - 1); break; case '-': ecbdata->lno_in_preimage++; emit_del_line(reset, ecbdata, line + 1, len - 1); break; case ' ': ecbdata->lno_in_postimage++; ecbdata->lno_in_preimage++; emit_context_line(reset, ecbdata, line + 1, len - 1); break; default: /* incomplete line at the end */ ecbdata->lno_in_preimage++; emit_line(o, diff_get_color(ecbdata->color_diff, DIFF_CONTEXT), reset, line, len); break; } } static char *pprint_rename(const char *a, const char *b) { const char *old = a; const char *new = b; struct strbuf name = STRBUF_INIT; 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 strbuf_detach(&name, NULL); } /* Find common prefix */ pfx_length = 0; while (*old && *new && *old == *new) { if (*old == '/') pfx_length = old - a + 1; old++; new++; } /* Find common suffix */ old = a + len_a; new = 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 && b + pfx_length - pfx_adjust_for_slash <= new && *old == *new) { if (*old == '/') sfx_length = len_a - (old - a); old--; new--; } /* * 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); } return strbuf_detach(&name, NULL); } struct diffstat_t { int nr; int alloc; struct diffstat_file { char *from_name; char *name; char *print_name; unsigned is_unmerged:1; unsigned is_binary:1; unsigned is_renamed:1; unsigned is_interesting:1; uintmax_t added, deleted; } **files; }; static struct diffstat_file *diffstat_add(struct diffstat_t *diffstat, const char *name_a, const char *name_b) { struct diffstat_file *x; x = xcalloc(1, sizeof(*x)); 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 void diffstat_consume(void *priv, char *line, unsigned long len) { struct diffstat_t *diffstat = priv; struct diffstat_file *x = diffstat->files[diffstat->nr - 1]; if (line[0] == '+') x->added++; else if (line[0] == '-') x->deleted++; } 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 alloted 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_name(FILE *file, const char *prefix, const char *name, int len) { fprintf(file, " %s%-*s |", prefix, len, name); } static void show_graph(FILE *file, char ch, int cnt, const char *set, const char *reset) { if (cnt <= 0) return; fprintf(file, "%s", set); while (cnt--) putc(ch, file); fprintf(file, "%s", reset); } static void fill_print_name(struct diffstat_file *file) { char *pname; if (file->print_name) return; if (!file->is_renamed) { struct strbuf buf = STRBUF_INIT; if (quote_c_style(file->name, &buf, NULL, 0)) { pname = strbuf_detach(&buf, NULL); } else { pname = file->name; strbuf_release(&buf); } } else { pname = pprint_rename(file->from_name, file->name); } file->print_name = pname; } int print_stat_summary(FILE *fp, int files, int insertions, int deletions) { struct strbuf sb = STRBUF_INIT; int ret; if (!files) { assert(insertions == 0 && deletions == 0); return fprintf(fp, "%s\n", " 0 files changed"); } 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'); ret = fputs(sb.buf, fp); strbuf_release(&sb); return ret; } 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; const char *line_prefix = ""; int extra_shown = 0; if (data->nr == 0) return; line_prefix = diff_line_prefix(options); 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 = strlen(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. */ 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; if (!file->is_interesting && (added + deleted == 0)) continue; /* * "scale" the filename */ len = name_width; name_len = strlen(name); if (name_width < name_len) { char *slash; prefix = "..."; len -= 3; name += name_len - len; slash = strchr(name, '/'); if (slash) name = slash; } if (file->is_binary) { fprintf(options->file, "%s", line_prefix); show_name(options->file, prefix, name, len); fprintf(options->file, " %*s", number_width, "Bin"); if (!added && !deleted) { putc('\n', options->file); continue; } fprintf(options->file, " %s%"PRIuMAX"%s", del_c, deleted, reset); fprintf(options->file, " -> "); fprintf(options->file, "%s%"PRIuMAX"%s", add_c, added, reset); fprintf(options->file, " bytes"); fprintf(options->file, "\n"); continue; } else if (file->is_unmerged) { fprintf(options->file, "%s", line_prefix); show_name(options->file, prefix, name, len); fprintf(options->file, " Unmerged\n"); 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; } } fprintf(options->file, "%s", line_prefix); show_name(options->file, prefix, name, len); fprintf(options->file, " %*"PRIuMAX"%s", number_width, added + deleted, added + deleted ? " " : ""); show_graph(options->file, '+', add, add_c, reset); show_graph(options->file, '-', del, del_c, reset); fprintf(options->file, "\n"); } 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) fprintf(options->file, "%s ...\n", line_prefix); extra_shown = 1; } fprintf(options->file, "%s", line_prefix); print_stat_summary(options->file, total_files, adds, dels); } static void show_shortstats(struct diffstat_t *data, struct diff_options *options) { int i, adds = 0, dels = 0, total_files = data->nr; if (data->nr == 0) return; for (i = 0; i < data->nr; i++) { int added = data->files[i]->added; int deleted= data->files[i]->deleted; if (data->files[i]->is_unmerged || (!data->files[i]->is_interesting && (added + deleted == 0))) { total_files--; } else if (!data->files[i]->is_binary) { /* don't count bytes */ adds += added; dels += deleted; } } fprintf(options->file, "%s", diff_line_prefix(options)); print_stat_summary(options->file, total_files, adds, dels); } static void show_numstat(struct diffstat_t *data, struct diff_options *options) { int i; if (data->nr == 0) return; for (i = 0; i < data->nr; i++) { struct diffstat_file *file = data->files[i]; fprintf(options->file, "%s", diff_line_prefix(options)); if (file->is_binary) fprintf(options->file, "-\t-\t"); else fprintf(options->file, "%"PRIuMAX"\t%"PRIuMAX"\t", file->added, file->deleted); if (options->line_termination) { fill_print_name(file); if (!file->is_renamed) write_name_quoted(file->name, options->file, options->line_termination); else { fputs(file->print_name, options->file); putc(options->line_termination, options->file); } } else { if (file->is_renamed) { putc('\0', options->file); write_name_quoted(file->from_name, options->file, '\0'); } write_name_quoted(file->name, options->file, '\0'); } } } struct dirstat_file { const char *name; unsigned long changed; }; struct dirstat_dir { struct dirstat_file *files; int alloc, nr, permille, cumulative; }; static long gather_dirstat(struct diff_options *opt, struct dirstat_dir *dir, unsigned long changed, const char *base, int baselen) { unsigned long this_dir = 0; unsigned int sources = 0; const char *line_prefix = diff_line_prefix(opt); while (dir->nr) { struct dirstat_file *f = dir->files; int namelen = strlen(f->name); unsigned long this; char *slash; if (namelen < baselen) break; if (memcmp(f->name, base, baselen)) break; slash = strchr(f->name + baselen, '/'); if (slash) { int newbaselen = slash + 1 - f->name; this = gather_dirstat(opt, dir, changed, f->name, newbaselen); sources++; } else { this = f->changed; dir->files++; dir->nr--; sources += 2; } this_dir += this; } /* * We don't report dirstat's for * - the top level * - or cases where everything came from a single directory * under this directory (sources == 1). */ if (baselen && sources != 1) { if (this_dir) { int permille = this_dir * 1000 / changed; if (permille >= dir->permille) { fprintf(opt->file, "%s%4d.%01d%% %.*s\n", line_prefix, permille / 10, permille % 10, baselen, base); if (!dir->cumulative) return 0; } } } return this_dir; } static int dirstat_compare(const void *_a, const void *_b) { const struct dirstat_file *a = _a; const struct dirstat_file *b = _b; return strcmp(a->name, b->name); } static void show_dirstat(struct diff_options *options) { int i; unsigned long changed; struct dirstat_dir dir; struct diff_queue_struct *q = &diff_queued_diff; dir.files = NULL; dir.alloc = 0; dir.nr = 0; dir.permille = options->dirstat_permille; dir.cumulative = DIFF_OPT_TST(options, DIRSTAT_CUMULATIVE); changed = 0; for (i = 0; i < q->nr; i++) { struct diff_filepair *p = q->queue[i]; const char *name; unsigned long copied, added, damage; int content_changed; name = p->two->path ? p->two->path : p->one->path; if (p->one->oid_valid && p->two->oid_valid) content_changed = oidcmp(&p->one->oid, &p->two->oid); else content_changed = 1; if (!content_changed) { /* * The SHA1 has not changed, so pre-/post-content is * identical. We can therefore skip looking at the * file contents altogether. */ damage = 0; goto found_damage; } if (DIFF_OPT_TST(options, DIRSTAT_BY_FILE)) { /* * In --dirstat-by-file mode, we don't really need to * look at the actual file contents at all. * The fact that the SHA1 changed is enough for us to * add this file to the list of results * (with each file contributing equal damage). */ damage = 1; goto found_damage; } if (DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two)) { diff_populate_filespec(p->one, 0); diff_populate_filespec(p->two, 0); diffcore_count_changes(p->one, p->two, NULL, NULL, &copied, &added); diff_free_filespec_data(p->one); diff_free_filespec_data(p->two); } else if (DIFF_FILE_VALID(p->one)) { diff_populate_filespec(p->one, CHECK_SIZE_ONLY); copied = added = 0; diff_free_filespec_data(p->one); } else if (DIFF_FILE_VALID(p->two)) { diff_populate_filespec(p->two, CHECK_SIZE_ONLY); copied = 0; added = p->two->size; diff_free_filespec_data(p->two); } else continue; /* * Original minus copied is the removed material, * added is the new material. They are both damages * made to the preimage. * If the resulting damage is zero, we know that * diffcore_count_changes() considers the two entries to * be identical, but since content_changed is true, we * know that there must have been _some_ kind of change, * so we force all entries to have damage > 0. */ damage = (p->one->size - copied) + added; if (!damage) damage = 1; found_damage: ALLOC_GROW(dir.files, dir.nr + 1, dir.alloc); dir.files[dir.nr].name = name; dir.files[dir.nr].changed = damage; changed += damage; dir.nr++; } /* This can happen even with many files, if everything was renames */ if (!changed) return; /* Show all directories with more than x% of the changes */ QSORT(dir.files, dir.nr, dirstat_compare); gather_dirstat(options, &dir, changed, "", 0); } static void show_dirstat_by_line(struct diffstat_t *data, struct diff_options *options) { int i; unsigned long changed; struct dirstat_dir dir; if (data->nr == 0) return; dir.files = NULL; dir.alloc = 0; dir.nr = 0; dir.permille = options->dirstat_permille; dir.cumulative = DIFF_OPT_TST(options, DIRSTAT_CUMULATIVE); changed = 0; for (i = 0; i < data->nr; i++) { struct diffstat_file *file = data->files[i]; unsigned long damage = file->added + file->deleted; if (file->is_binary) /* * binary files counts bytes, not lines. Must find some * way to normalize binary bytes vs. textual lines. * The following heuristic assumes that there are 64 * bytes per "line". * This is stupid and ugly, but very cheap... */ damage = DIV_ROUND_UP(damage, 64); ALLOC_GROW(dir.files, dir.nr + 1, dir.alloc); dir.files[dir.nr].name = file->name; dir.files[dir.nr].changed = damage; changed += damage; dir.nr++; } /* This can happen even with many files, if everything was renames */ if (!changed) return; /* Show all directories with more than x% of the changes */ QSORT(dir.files, dir.nr, dirstat_compare); gather_dirstat(options, &dir, changed, "", 0); } static void free_diffstat_info(struct diffstat_t *diffstat) { int i; for (i = 0; i < diffstat->nr; i++) { struct diffstat_file *f = diffstat->files[i]; if (f->name != f->print_name) free(f->print_name); free(f->name); free(f->from_name); free(f); } free(diffstat->files); } struct checkdiff_t { const char *filename; int lineno; int conflict_marker_size; struct diff_options *o; unsigned ws_rule; unsigned status; }; static int is_conflict_marker(const char *line, int marker_size, unsigned long len) { char firstchar; int cnt; if (len < marker_size + 1) return 0; firstchar = line[0]; switch (firstchar) { case '=': case '>': case '<': case '|': break; default: return 0; } for (cnt = 1; cnt < marker_size; cnt++) if (line[cnt] != firstchar) return 0; /* line[1] thru line[marker_size-1] are same as firstchar */ if (len < marker_size + 1 || !isspace(line[marker_size])) return 0; return 1; } static void checkdiff_consume(void *priv, char *line, unsigned long len) { struct checkdiff_t *data = priv; int marker_size = data->conflict_marker_size; const char *ws = diff_get_color(data->o->use_color, DIFF_WHITESPACE); const char *reset = diff_get_color(data->o->use_color, DIFF_RESET); const char *set = diff_get_color(data->o->use_color, DIFF_FILE_NEW); char *err; const char *line_prefix; assert(data->o); line_prefix = diff_line_prefix(data->o); if (line[0] == '+') { unsigned bad; data->lineno++; if (is_conflict_marker(line + 1, marker_size, len - 1)) { data->status |= 1; fprintf(data->o->file, "%s%s:%d: leftover conflict marker\n", line_prefix, data->filename, data->lineno); } bad = ws_check(line + 1, len - 1, data->ws_rule); if (!bad) return; data->status |= bad; err = whitespace_error_string(bad); fprintf(data->o->file, "%s%s:%d: %s.\n", line_prefix, data->filename, data->lineno, err); free(err); emit_line(data->o, set, reset, line, 1); ws_check_emit(line + 1, len - 1, data->ws_rule, data->o->file, set, reset, ws); } else if (line[0] == ' ') { data->lineno++; } else if (line[0] == '@') { char *plus = strchr(line, '+'); if (plus) data->lineno = strtol(plus, NULL, 10) - 1; else die("invalid diff"); } } static unsigned char *deflate_it(char *data, unsigned long size, unsigned long *result_size) { int bound; unsigned char *deflated; git_zstream stream; git_deflate_init(&stream, zlib_compression_level); bound = git_deflate_bound(&stream, size); deflated = xmalloc(bound); stream.next_out = deflated; stream.avail_out = bound; stream.next_in = (unsigned char *)data; stream.avail_in = size; while (git_deflate(&stream, Z_FINISH) == Z_OK) ; /* nothing */ git_deflate_end(&stream); *result_size = stream.total_out; return deflated; } static void emit_binary_diff_body(FILE *file, mmfile_t *one, mmfile_t *two, const char *prefix) { void *cp; void *delta; void *deflated; void *data; unsigned long orig_size; unsigned long delta_size; unsigned long deflate_size; unsigned long data_size; /* We could do deflated delta, or we could do just deflated two, * whichever is smaller. */ delta = NULL; deflated = deflate_it(two->ptr, two->size, &deflate_size); if (one->size && two->size) { delta = diff_delta(one->ptr, one->size, two->ptr, two->size, &delta_size, deflate_size); if (delta) { void *to_free = delta; orig_size = delta_size; delta = deflate_it(delta, delta_size, &delta_size); free(to_free); } } if (delta && delta_size < deflate_size) { fprintf(file, "%sdelta %lu\n", prefix, orig_size); free(deflated); data = delta; data_size = delta_size; } else { fprintf(file, "%sliteral %lu\n", prefix, two->size); free(delta); data = deflated; data_size = deflate_size; } /* emit data encoded in base85 */ cp = data; while (data_size) { int bytes = (52 < data_size) ? 52 : data_size; char line[70]; data_size -= bytes; if (bytes <= 26) line[0] = bytes + 'A' - 1; else line[0] = bytes - 26 + 'a' - 1; encode_85(line + 1, cp, bytes); cp = (char *) cp + bytes; fprintf(file, "%s", prefix); fputs(line, file); fputc('\n', file); } fprintf(file, "%s\n", prefix); free(data); } static void emit_binary_diff(FILE *file, mmfile_t *one, mmfile_t *two, const char *prefix) { fprintf(file, "%sGIT binary patch\n", prefix); emit_binary_diff_body(file, one, two, prefix); emit_binary_diff_body(file, two, one, prefix); } int diff_filespec_is_binary(struct diff_filespec *one) { if (one->is_binary == -1) { diff_filespec_load_driver(one); if (one->driver->binary != -1) one->is_binary = one->driver->binary; else { if (!one->data && DIFF_FILE_VALID(one)) diff_populate_filespec(one, CHECK_BINARY); if (one->is_binary == -1 && one->data) one->is_binary = buffer_is_binary(one->data, one->size); if (one->is_binary == -1) one->is_binary = 0; } } return one->is_binary; } static const struct userdiff_funcname *diff_funcname_pattern(struct diff_filespec *one) { diff_filespec_load_driver(one); return one->driver->funcname.pattern ? &one->driver->funcname : NULL; } void diff_set_mnemonic_prefix(struct diff_options *options, const char *a, const char *b) { if (!options->a_prefix) options->a_prefix = a; if (!options->b_prefix) options->b_prefix = b; } struct userdiff_driver *get_textconv(struct diff_filespec *one) { if (!DIFF_FILE_VALID(one)) return NULL; diff_filespec_load_driver(one); return userdiff_get_textconv(one->driver); } static void builtin_diff(const char *name_a, const char *name_b, struct diff_filespec *one, struct diff_filespec *two, const char *xfrm_msg, int must_show_header, struct diff_options *o, int complete_rewrite) { mmfile_t mf1, mf2; const char *lbl[2]; char *a_one, *b_two; const char *meta = diff_get_color_opt(o, DIFF_METAINFO); const char *reset = diff_get_color_opt(o, DIFF_RESET); const char *a_prefix, *b_prefix; struct userdiff_driver *textconv_one = NULL; struct userdiff_driver *textconv_two = NULL; struct strbuf header = STRBUF_INIT; const char *line_prefix = diff_line_prefix(o); diff_set_mnemonic_prefix(o, "a/", "b/"); if (DIFF_OPT_TST(o, REVERSE_DIFF)) { a_prefix = o->b_prefix; b_prefix = o->a_prefix; } else { a_prefix = o->a_prefix; b_prefix = o->b_prefix; } if (o->submodule_format == DIFF_SUBMODULE_LOG && (!one->mode || S_ISGITLINK(one->mode)) && (!two->mode || S_ISGITLINK(two->mode))) { const char *del = diff_get_color_opt(o, DIFF_FILE_OLD); const char *add = diff_get_color_opt(o, DIFF_FILE_NEW); show_submodule_summary(o->file, one->path ? one->path : two->path, line_prefix, &one->oid, &two->oid, two->dirty_submodule, meta, del, add, reset); return; } else if (o->submodule_format == DIFF_SUBMODULE_INLINE_DIFF && (!one->mode || S_ISGITLINK(one->mode)) && (!two->mode || S_ISGITLINK(two->mode))) { const char *del = diff_get_color_opt(o, DIFF_FILE_OLD); const char *add = diff_get_color_opt(o, DIFF_FILE_NEW); show_submodule_inline_diff(o->file, one->path ? one->path : two->path, line_prefix, &one->oid, &two->oid, two->dirty_submodule, meta, del, add, reset, o); return; } if (DIFF_OPT_TST(o, ALLOW_TEXTCONV)) { textconv_one = get_textconv(one); textconv_two = get_textconv(two); } /* Never use a non-valid filename anywhere if at all possible */ name_a = DIFF_FILE_VALID(one) ? name_a : name_b; name_b = DIFF_FILE_VALID(two) ? name_b : name_a; a_one = quote_two(a_prefix, name_a + (*name_a == '/')); b_two = quote_two(b_pre