From 25ed3412f86b136efb17689b6712d9e546cac388 Mon Sep 17 00:00:00 2001 From: Bo Yang Date: Thu, 28 Mar 2013 17:47:30 +0100 Subject: [PATCH 01/13] Refactor parse_loc We want to use the same style of -L n,m argument for 'git log -L' as for git-blame. Refactor the argument parsing of the range arguments from builtin/blame.c to the (new) file that will hold the 'git log -L' logic. To accommodate different data structures in blame and log -L, the file contents are abstracted away; parse_range_arg takes a callback that it uses to get the contents of a line of the (notional) file. The new test is for a case that made me pause during debugging: the 'blame -L with invalid end' test was the only one that noticed an outright failure to parse the end *at all*. So make a more explicit test for that. Signed-off-by: Bo Yang Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- Documentation/blame-options.txt | 19 +----- Documentation/line-range-format.txt | 18 ++++++ Makefile | 2 + builtin/blame.c | 99 +++-------------------------- line-range.c | 92 +++++++++++++++++++++++++++ line-range.h | 24 +++++++ t/t8003-blame-corner-cases.sh | 6 ++ 7 files changed, 151 insertions(+), 109 deletions(-) create mode 100644 Documentation/line-range-format.txt create mode 100644 line-range.c create mode 100644 line-range.h diff --git a/Documentation/blame-options.txt b/Documentation/blame-options.txt index b0d31df0e7..6998d9f5bf 100644 --- a/Documentation/blame-options.txt +++ b/Documentation/blame-options.txt @@ -13,24 +13,7 @@ Annotate only the given line range. and can take one of these forms: - - number -+ -If or is a number, it specifies an -absolute line number (lines count from 1). -+ - -- /regex/ -+ -This form will use the first line matching the given -POSIX regex. If is a regex, it will search -starting at the line given by . -+ - -- +offset or -offset -+ -This is only valid for and will specify a number -of lines before or after the line given by . -+ +include::line-range-format.txt[] -l:: Show long rev (Default: off). diff --git a/Documentation/line-range-format.txt b/Documentation/line-range-format.txt new file mode 100644 index 0000000000..265bc23290 --- /dev/null +++ b/Documentation/line-range-format.txt @@ -0,0 +1,18 @@ +- number ++ +If or is a number, it specifies an +absolute line number (lines count from 1). ++ + +- /regex/ ++ +This form will use the first line matching the given +POSIX regex. If is a regex, it will search +starting at the line given by . ++ + +- +offset or -offset ++ +This is only valid for and will specify a number +of lines before or after the line given by . ++ diff --git a/Makefile b/Makefile index 26d3332755..89242f5929 100644 --- a/Makefile +++ b/Makefile @@ -683,6 +683,7 @@ LIB_H += help.h LIB_H += http.h LIB_H += kwset.h LIB_H += levenshtein.h +LIB_H += line-range.h LIB_H += list-objects.h LIB_H += ll-merge.h LIB_H += log-tree.h @@ -798,6 +799,7 @@ LIB_OBJS += hex.o LIB_OBJS += ident.o LIB_OBJS += kwset.o LIB_OBJS += levenshtein.o +LIB_OBJS += line-range.o LIB_OBJS += list-objects.o LIB_OBJS += ll-merge.o LIB_OBJS += lockfile.o diff --git a/builtin/blame.c b/builtin/blame.c index 86100e9662..20eb439cb8 100644 --- a/builtin/blame.c +++ b/builtin/blame.c @@ -21,6 +21,7 @@ #include "parse-options.h" #include "utf8.h" #include "userdiff.h" +#include "line-range.h" static char blame_usage[] = N_("git blame [options] [rev-opts] [rev] [--] file"); @@ -566,11 +567,16 @@ static void dup_entry(struct blame_entry *dst, struct blame_entry *src) dst->score = 0; } -static const char *nth_line(struct scoreboard *sb, int lno) +static const char *nth_line(struct scoreboard *sb, long lno) { return sb->final_buf + sb->lineno[lno]; } +static const char *nth_line_cb(void *data, long lno) +{ + return nth_line((struct scoreboard *)data, lno); +} + /* * It is known that lines between tlno to same came from parent, and e * has an overlap with that range. it also is known that parent's @@ -1926,83 +1932,6 @@ static const char *add_prefix(const char *prefix, const char *path) return prefix_path(prefix, prefix ? strlen(prefix) : 0, path); } -/* - * Parsing of (comma separated) one item in the -L option - */ -static const char *parse_loc(const char *spec, - struct scoreboard *sb, long lno, - long begin, long *ret) -{ - char *term; - const char *line; - long num; - int reg_error; - regex_t regexp; - regmatch_t match[1]; - - /* Allow "-L ,+20" to mean starting at - * for 20 lines, or "-L ,-5" for 5 lines ending at - * . - */ - if (1 < begin && (spec[0] == '+' || spec[0] == '-')) { - num = strtol(spec + 1, &term, 10); - if (term != spec + 1) { - if (spec[0] == '-') - num = 0 - num; - if (0 < num) - *ret = begin + num - 2; - else if (!num) - *ret = begin; - else - *ret = begin + num; - return term; - } - return spec; - } - num = strtol(spec, &term, 10); - if (term != spec) { - *ret = num; - return term; - } - if (spec[0] != '/') - return spec; - - /* it could be a regexp of form /.../ */ - for (term = (char *) spec + 1; *term && *term != '/'; term++) { - if (*term == '\\') - term++; - } - if (*term != '/') - return spec; - - /* try [spec+1 .. term-1] as regexp */ - *term = 0; - begin--; /* input is in human terms */ - line = nth_line(sb, begin); - - if (!(reg_error = regcomp(®exp, spec + 1, REG_NEWLINE)) && - !(reg_error = regexec(®exp, line, 1, match, 0))) { - const char *cp = line + match[0].rm_so; - const char *nline; - - while (begin++ < lno) { - nline = nth_line(sb, begin); - if (line <= cp && cp < nline) - break; - line = nline; - } - *ret = begin; - regfree(®exp); - *term++ = '/'; - return term; - } - else { - char errbuf[1024]; - regerror(reg_error, ®exp, errbuf, 1024); - die("-L parameter '%s': %s", spec + 1, errbuf); - } -} - /* * Parsing of -L option */ @@ -2011,15 +1940,7 @@ static void prepare_blame_range(struct scoreboard *sb, long lno, long *bottom, long *top) { - const char *term; - - term = parse_loc(bottomtop, sb, lno, 1, bottom); - if (*term == ',') { - term = parse_loc(term + 1, sb, lno, *bottom + 1, top); - if (*term) - usage(blame_usage); - } - if (*term) + if (parse_range_arg(bottomtop, nth_line_cb, sb, lno, bottom, top)) usage(blame_usage); } @@ -2569,10 +2490,6 @@ parse_done: bottom = top = 0; if (bottomtop) prepare_blame_range(&sb, bottomtop, lno, &bottom, &top); - if (bottom && top && top < bottom) { - long tmp; - tmp = top; top = bottom; bottom = tmp; - } if (bottom < 1) bottom = 1; if (top < 1) diff --git a/line-range.c b/line-range.c new file mode 100644 index 0000000000..5a226abdd0 --- /dev/null +++ b/line-range.c @@ -0,0 +1,92 @@ +#include "git-compat-util.h" +#include "line-range.h" + +/* + * Parse one item in the -L option + */ +static const char *parse_loc(const char *spec, nth_line_fn_t nth_line, + void *data, long lines, long begin, long *ret) +{ + char *term; + const char *line; + long num; + int reg_error; + regex_t regexp; + regmatch_t match[1]; + + /* Allow "-L ,+20" to mean starting at + * for 20 lines, or "-L ,-5" for 5 lines ending at + * . + */ + if (1 < begin && (spec[0] == '+' || spec[0] == '-')) { + num = strtol(spec + 1, &term, 10); + if (term != spec + 1) { + if (spec[0] == '-') + num = 0 - num; + if (0 < num) + *ret = begin + num - 2; + else if (!num) + *ret = begin; + else + *ret = begin + num; + return term; + } + return spec; + } + num = strtol(spec, &term, 10); + if (term != spec) { + *ret = num; + return term; + } + if (spec[0] != '/') + return spec; + + /* it could be a regexp of form /.../ */ + for (term = (char *) spec + 1; *term && *term != '/'; term++) { + if (*term == '\\') + term++; + } + if (*term != '/') + return spec; + + /* try [spec+1 .. term-1] as regexp */ + *term = 0; + begin--; /* input is in human terms */ + line = nth_line(data, begin); + + if (!(reg_error = regcomp(®exp, spec + 1, REG_NEWLINE)) && + !(reg_error = regexec(®exp, line, 1, match, 0))) { + const char *cp = line + match[0].rm_so; + const char *nline; + + while (begin++ < lines) { + nline = nth_line(data, begin); + if (line <= cp && cp < nline) + break; + line = nline; + } + *ret = begin; + regfree(®exp); + *term++ = '/'; + return term; + } + else { + char errbuf[1024]; + regerror(reg_error, ®exp, errbuf, 1024); + die("-L parameter '%s': %s", spec + 1, errbuf); + } +} + +int parse_range_arg(const char *arg, nth_line_fn_t nth_line_cb, + void *cb_data, long lines, long *begin, long *end) +{ + arg = parse_loc(arg, nth_line_cb, cb_data, lines, 1, begin); + + if (*arg == ',') + arg = parse_loc(arg + 1, nth_line_cb, cb_data, lines, *begin + 1, end); + + if (*arg) + return -1; + + return 0; +} diff --git a/line-range.h b/line-range.h new file mode 100644 index 0000000000..830f25b501 --- /dev/null +++ b/line-range.h @@ -0,0 +1,24 @@ +#ifndef LINE_RANGE_H +#define LINE_RANGE_H + +/* + * Parse one item in an -L begin,end option w.r.t. the notional file + * object 'cb_data' consisting of 'lines' lines. + * + * The 'nth_line_cb' callback is used to determine the start of the + * line 'lno' inside the 'cb_data'. The caller is expected to already + * have a suitable map at hand to make this a constant-time lookup. + * + * Returns 0 in case of success and -1 if there was an error. The + * actual range is stored in *begin and *end. The counting starts + * at 1! In case of error, the caller should show usage message. + */ + +typedef const char *(*nth_line_fn_t)(void *data, long lno); + +extern int parse_range_arg(const char *arg, + nth_line_fn_t nth_line_cb, + void *cb_data, long lines, + long *begin, long *end); + +#endif /* LINE_RANGE_H */ diff --git a/t/t8003-blame-corner-cases.sh b/t/t8003-blame-corner-cases.sh index 230143cf31..e7cac1db55 100755 --- a/t/t8003-blame-corner-cases.sh +++ b/t/t8003-blame-corner-cases.sh @@ -175,6 +175,12 @@ test_expect_success 'blame -L with invalid end' ' grep "has only 2 lines" errors ' +test_expect_success 'blame parses part of -L' ' + git blame -L1,1 tres >out && + cat out && + test $(wc -l < out) -eq 1 +' + test_expect_success 'indent of line numbers, nine lines' ' git blame nine_lines >actual && test $(grep -c " " actual) = 0 From c7edcae06ed90ec0567179a78d7d1170e610c042 Mon Sep 17 00:00:00 2001 From: Bo Yang Date: Thu, 28 Mar 2013 17:47:31 +0100 Subject: [PATCH 02/13] Export rewrite_parents() for 'log -L' The function rewrite_one is used to rewrite a single parent of the current commit, and is used by rewrite_parents to rewrite all the parents. Decouple the dependence between them by making rewrite_one a callback function that is passed to rewrite_parents. Then export rewrite_parents for reuse by the line history browser. We will use this function in line-log.c. Signed-off-by: Bo Yang Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- revision.c | 13 ++++--------- revision.h | 10 ++++++++++ 2 files changed, 14 insertions(+), 9 deletions(-) diff --git a/revision.c b/revision.c index ef60205412..46319d52b4 100644 --- a/revision.c +++ b/revision.c @@ -2173,12 +2173,6 @@ int prepare_revision_walk(struct rev_info *revs) return 0; } -enum rewrite_result { - rewrite_one_ok, - rewrite_one_noparents, - rewrite_one_error -}; - static enum rewrite_result rewrite_one(struct rev_info *revs, struct commit **pp) { struct commit_list *cache = NULL; @@ -2200,12 +2194,13 @@ static enum rewrite_result rewrite_one(struct rev_info *revs, struct commit **pp } } -static int rewrite_parents(struct rev_info *revs, struct commit *commit) +int rewrite_parents(struct rev_info *revs, struct commit *commit, + rewrite_parent_fn_t rewrite_parent) { struct commit_list **pp = &commit->parents; while (*pp) { struct commit_list *parent = *pp; - switch (rewrite_one(revs, &parent->item)) { + switch (rewrite_parent(revs, &parent->item)) { case rewrite_one_ok: break; case rewrite_one_noparents: @@ -2371,7 +2366,7 @@ enum commit_action simplify_commit(struct rev_info *revs, struct commit *commit) if (action == commit_show && !revs->show_all && revs->prune && revs->dense && want_ancestry(revs)) { - if (rewrite_parents(revs, commit) < 0) + if (rewrite_parents(revs, commit, rewrite_one) < 0) return commit_error; } return action; diff --git a/revision.h b/revision.h index 5da09ee3ef..640110d73e 100644 --- a/revision.h +++ b/revision.h @@ -241,4 +241,14 @@ enum commit_action { extern enum commit_action get_commit_action(struct rev_info *revs, struct commit *commit); extern enum commit_action simplify_commit(struct rev_info *revs, struct commit *commit); +enum rewrite_result { + rewrite_one_ok, + rewrite_one_noparents, + rewrite_one_error +}; + +typedef enum rewrite_result (*rewrite_parent_fn_t)(struct rev_info *revs, struct commit **pp); + +extern int rewrite_parents(struct rev_info *revs, struct commit *commit, + rewrite_parent_fn_t rewrite_parent); #endif From 12da1d1f6ffcd546a892a33302bb34fd37169022 Mon Sep 17 00:00:00 2001 From: Thomas Rast Date: Thu, 28 Mar 2013 17:47:32 +0100 Subject: [PATCH 03/13] Implement line-history search (git log -L) This is a rewrite of much of Bo's work, mainly in an effort to split it into smaller, easier to understand routines. The algorithm is built around the struct range_set, which encodes a series of line ranges as intervals [a,b). This is used in two contexts: * A set of lines we are tracking (which will change as we dig through history). * To encode diffs, as pairs of ranges. The main routine is range_set_map_across_diff(). It processes the diff between a commit C and some parent P. It determines which diff hunks are relevant to the ranges tracked in C, and computes the new ranges for P. The algorithm is then simply to process history in topological order from newest to oldest, computing ranges and (partial) diffs. At branch points, we need to merge the ranges we are watching. We will find that many commits do not affect the chosen ranges, and mark them TREESAME (in addition to those already filtered by pathspec limiting). Another pass of history simplification then gets rid of such commits. This is wired as an extra filtering pass in the log machinery. This currently only reduces code duplication, but should allow for other simplifications and options to be used. Finally, we hook a diff printer into the output chain. Ideally we would wire directly into the diff logic, to optionally use features like word diff. However, that will require some major reworking of the diff chain, so we completely replace the output with our own diff for now. As this was a GSoC project, and has quite some history by now, many people have helped. In no particular order, thanks go to Jakub Narebski Jens Lehmann Jonathan Nieder Junio C Hamano Ramsay Jones Will Palmer Apologies to everyone I forgot. Signed-off-by: Bo Yang Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- Documentation/git-log.txt | 22 + Makefile | 2 + builtin/log.c | 31 + line-log.c | 1179 ++++++++++++++++++++++++++++++ line-log.h | 49 ++ line-range.c | 19 +- line-range.h | 11 + log-tree.c | 4 + revision.c | 9 + revision.h | 6 +- t/perf/p4211-line-log.sh | 34 + t/t4211-line-log.sh | 49 ++ t/t4211/expect.beginning-of-file | 43 ++ t/t4211/expect.end-of-file | 62 ++ t/t4211/expect.move-support-f | 40 + t/t4211/expect.simple-f | 59 ++ t/t4211/expect.simple-main | 68 ++ t/t4211/expect.two-ranges | 102 +++ t/t4211/expect.vanishes-early | 39 + t/t4211/history.export | 330 +++++++++ 20 files changed, 2156 insertions(+), 2 deletions(-) create mode 100644 line-log.c create mode 100644 line-log.h create mode 100755 t/perf/p4211-line-log.sh create mode 100755 t/t4211-line-log.sh create mode 100644 t/t4211/expect.beginning-of-file create mode 100644 t/t4211/expect.end-of-file create mode 100644 t/t4211/expect.move-support-f create mode 100644 t/t4211/expect.simple-f create mode 100644 t/t4211/expect.simple-main create mode 100644 t/t4211/expect.two-ranges create mode 100644 t/t4211/expect.vanishes-early create mode 100644 t/t4211/history.export diff --git a/Documentation/git-log.txt b/Documentation/git-log.txt index 69db5783ce..8727c60ab3 100644 --- a/Documentation/git-log.txt +++ b/Documentation/git-log.txt @@ -69,6 +69,23 @@ produced by --stat etc. Note that only message is considered, if also a diff is shown its size is not included. +-L ,::: + Trace the evolution of the line range given by "," + within the . You may not give any pathspec limiters. + This is currently limited to a walk starting from a single + revision, i.e., you may only give zero or one positive + revision arguments. + + and can take one of these forms: + +include::line-range-format.txt[] +You can specify this option more than once. + + +--full-line-diff:: + Always print the interesting range even if the current commit + does not change any line of the range. + [\--] ...:: Show only commits that are enough to explain how the files that match the specified paths came to be. See "History @@ -138,6 +155,11 @@ Examples This makes sense only when following a strict policy of merging all topic branches when staying on a single integration branch. +git log -L '/int main/',/^}/:main.c:: + + Shows how the function `main()` in the file 'main.c' evolved + over time. + `git log -3`:: Limits the number of commits to show to 3. diff --git a/Makefile b/Makefile index 89242f5929..761c698a62 100644 --- a/Makefile +++ b/Makefile @@ -683,6 +683,7 @@ LIB_H += help.h LIB_H += http.h LIB_H += kwset.h LIB_H += levenshtein.h +LIB_H += line-log.h LIB_H += line-range.h LIB_H += list-objects.h LIB_H += ll-merge.h @@ -799,6 +800,7 @@ LIB_OBJS += hex.o LIB_OBJS += ident.o LIB_OBJS += kwset.o LIB_OBJS += levenshtein.o +LIB_OBJS += line-log.o LIB_OBJS += line-range.o LIB_OBJS += list-objects.o LIB_OBJS += ll-merge.o diff --git a/builtin/log.c b/builtin/log.c index 8f0b2e84fe..d584ff1a39 100644 --- a/builtin/log.c +++ b/builtin/log.c @@ -19,6 +19,7 @@ #include "remote.h" #include "string-list.h" #include "parse-options.h" +#include "line-log.h" #include "branch.h" #include "streaming.h" #include "version.h" @@ -41,6 +42,12 @@ static const char * const builtin_log_usage[] = { NULL }; +struct line_opt_callback_data { + struct rev_info *rev; + const char *prefix; + struct string_list args; +}; + static int parse_decoration_style(const char *var, const char *value) { switch (git_config_maybe_bool(var, value)) { @@ -75,6 +82,19 @@ static int decorate_callback(const struct option *opt, const char *arg, int unse return 0; } +static int log_line_range_callback(const struct option *option, const char *arg, int unset) +{ + struct line_opt_callback_data *data = option->value; + + if (!arg) + return -1; + + data->rev->line_level_traverse = 1; + string_list_append(&data->args, arg); + + return 0; +} + static void cmd_log_init_defaults(struct rev_info *rev) { if (fmt_pretty) @@ -97,6 +117,7 @@ static void cmd_log_init_finish(int argc, const char **argv, const char *prefix, { struct userformat_want w; int quiet = 0, source = 0, mailmap = 0; + static struct line_opt_callback_data line_cb = {NULL, NULL, STRING_LIST_INIT_DUP}; const struct option builtin_log_options[] = { OPT_BOOLEAN(0, "quiet", &quiet, N_("suppress diff output")), @@ -104,9 +125,15 @@ static void cmd_log_init_finish(int argc, const char **argv, const char *prefix, OPT_BOOLEAN(0, "use-mailmap", &mailmap, N_("Use mail map file")), { OPTION_CALLBACK, 0, "decorate", NULL, NULL, N_("decorate options"), PARSE_OPT_OPTARG, decorate_callback}, + OPT_CALLBACK('L', NULL, &line_cb, "n,m:file", + "Process line range n,m in file, counting from 1", + log_line_range_callback), OPT_END() }; + line_cb.rev = rev; + line_cb.prefix = prefix; + mailmap = use_mailmap_config; argc = parse_options(argc, argv, prefix, builtin_log_options, builtin_log_usage, @@ -160,6 +187,10 @@ static void cmd_log_init_finish(int argc, const char **argv, const char *prefix, rev->show_decorations = 1; load_ref_decorations(decoration_style); } + + if (rev->line_level_traverse) + line_log_init(rev, line_cb.prefix, &line_cb.args); + setup_pager(); } diff --git a/line-log.c b/line-log.c new file mode 100644 index 0000000000..624423142e --- /dev/null +++ b/line-log.c @@ -0,0 +1,1179 @@ +#include "git-compat-util.h" +#include "line-range.h" +#include "cache.h" +#include "tag.h" +#include "blob.h" +#include "tree.h" +#include "diff.h" +#include "commit.h" +#include "decorate.h" +#include "revision.h" +#include "xdiff-interface.h" +#include "strbuf.h" +#include "log-tree.h" +#include "graph.h" +#include "line-log.h" + +static void range_set_grow(struct range_set *rs, size_t extra) +{ + ALLOC_GROW(rs->ranges, rs->nr + extra, rs->alloc); +} + +/* Either initialization would be fine */ +#define RANGE_SET_INIT {0} + +static void range_set_init(struct range_set *rs, size_t prealloc) +{ + rs->alloc = rs->nr = 0; + rs->ranges = NULL; + if (prealloc) + range_set_grow(rs, prealloc); +} + +static void range_set_release(struct range_set *rs) +{ + free(rs->ranges); + rs->alloc = rs->nr = 0; + rs->ranges = NULL; +} + +/* dst must be uninitialized! */ +static void range_set_copy(struct range_set *dst, struct range_set *src) +{ + range_set_init(dst, src->nr); + memcpy(dst->ranges, src->ranges, src->nr*sizeof(struct range_set)); + dst->nr = src->nr; +} +static void range_set_move(struct range_set *dst, struct range_set *src) +{ + range_set_release(dst); + dst->ranges = src->ranges; + dst->nr = src->nr; + dst->alloc = src->alloc; + src->ranges = NULL; + src->alloc = src->nr = 0; +} + +/* tack on a _new_ range _at the end_ */ +static void range_set_append(struct range_set *rs, long a, long b) +{ + assert(a <= b); + assert(rs->nr == 0 || rs->ranges[rs->nr-1].end <= a); + range_set_grow(rs, 1); + rs->ranges[rs->nr].start = a; + rs->ranges[rs->nr].end = b; + rs->nr++; +} + +static int range_cmp(const void *_r, const void *_s) +{ + const struct range *r = _r; + const struct range *s = _s; + + /* this could be simply 'return r.start-s.start', but for the types */ + if (r->start == s->start) + return 0; + if (r->start < s->start) + return -1; + return 1; +} + +/* + * Helper: In-place pass of sorting and merging the ranges in the + * range set, to re-establish the invariants after another operation + * + * NEEDSWORK currently not needed + */ +static void sort_and_merge_range_set(struct range_set *rs) +{ + int i; + int o = 1; /* output cursor */ + + qsort(rs->ranges, rs->nr, sizeof(struct range), range_cmp); + + for (i = 1; i < rs->nr; i++) { + if (rs->ranges[i].start <= rs->ranges[o-1].end) { + rs->ranges[o-1].end = rs->ranges[i].end; + } else { + rs->ranges[o].start = rs->ranges[i].start; + rs->ranges[o].end = rs->ranges[i].end; + o++; + } + } + assert(o <= rs->nr); + rs->nr = o; +} + +/* + * Union of range sets (i.e., sets of line numbers). Used to merge + * them when searches meet at a common ancestor. + * + * This is also where the ranges are consolidated into canonical form: + * overlapping and adjacent ranges are merged, and empty ranges are + * removed. + */ +static void range_set_union(struct range_set *out, + struct range_set *a, struct range_set *b) +{ + int i = 0, j = 0, o = 0; + struct range *ra = a->ranges; + struct range *rb = b->ranges; + /* cannot make an alias of out->ranges: it may change during grow */ + + assert(out->nr == 0); + while (i < a->nr || j < b->nr) { + struct range *new; + if (i < a->nr && j < b->nr) { + if (ra[i].start < rb[j].start) + new = &ra[i++]; + else if (ra[i].start > rb[j].start) + new = &rb[j++]; + else if (ra[i].end < rb[j].end) + new = &ra[i++]; + else + new = &rb[j++]; + } else if (i < a->nr) /* b exhausted */ + new = &ra[i++]; + else /* a exhausted */ + new = &rb[j++]; + if (new->start == new->end) + ; /* empty range */ + else if (!o || out->ranges[o-1].end < new->start) { + range_set_grow(out, 1); + out->ranges[o].start = new->start; + out->ranges[o].end = new->end; + o++; + } else if (out->ranges[o-1].end < new->end) { + out->ranges[o-1].end = new->end; + } + } + out->nr = o; +} + +/* + * Difference of range sets (out = a \ b). Pass the "interesting" + * ranges as 'a' and the target side of the diff as 'b': it removes + * the ranges for which the commit is responsible. + */ +static void range_set_difference(struct range_set *out, + struct range_set *a, struct range_set *b) +{ + int i, j = 0; + for (i = 0; i < a->nr; i++) { + long start = a->ranges[i].start; + long end = a->ranges[i].end; + while (start < end) { + while (j < b->nr && start >= b->ranges[j].end) + /* + * a: |------- + * b: ------| + */ + j++; + if (j >= b->nr || end < b->ranges[j].start) { + /* + * b exhausted, or + * a: ----| + * b: |---- + */ + range_set_append(out, start, end); + break; + } + if (start >= b->ranges[j].start) { + /* + * a: |--???? + * b: |------| + */ + start = b->ranges[j].end; + } else if (end > b->ranges[j].start) { + /* + * a: |-----| + * b: |--????? + */ + if (start < b->ranges[j].start) + range_set_append(out, start, b->ranges[j].start); + start = b->ranges[j].end; + } + } + } +} + +static void diff_ranges_init(struct diff_ranges *diff) +{ + range_set_init(&diff->parent, 0); + range_set_init(&diff->target, 0); +} + +static void diff_ranges_release(struct diff_ranges *diff) +{ + range_set_release(&diff->parent); + range_set_release(&diff->target); +} + +void line_log_data_init(struct line_log_data *r) +{ + memset(r, 0, sizeof(struct line_log_data)); + range_set_init(&r->ranges, 0); +} + +static void line_log_data_clear(struct line_log_data *r) +{ + range_set_release(&r->ranges); + if (r->pair) + diff_free_filepair(r->pair); +} + +static void free_line_log_data(struct line_log_data *r) +{ + while (r) { + struct line_log_data *next = r->next; + line_log_data_clear(r); + free(r); + r = next; + } +} + +static struct line_log_data * +search_line_log_data(struct line_log_data *list, const char *path, + struct line_log_data **insertion_point) +{ + struct line_log_data *p = list; + if (insertion_point) + *insertion_point = NULL; + while (p) { + int cmp = strcmp(p->spec->path, path); + if (!cmp) + return p; + if (insertion_point && cmp < 0) + *insertion_point = p; + p = p->next; + } + return NULL; +} + +static void line_log_data_insert(struct line_log_data **list, + struct diff_filespec *spec, + long begin, long end) +{ + struct line_log_data *ip; + struct line_log_data *p = search_line_log_data(*list, spec->path, &ip); + + if (p) { + range_set_append(&p->ranges, begin, end); + sort_and_merge_range_set(&p->ranges); + free_filespec(spec); + return; + } + + p = xcalloc(1, sizeof(struct line_log_data)); + p->spec = spec; + range_set_append(&p->ranges, begin, end); + if (ip) { + p->next = ip->next; + ip->next = p; + } else { + p->next = *list; + *list = p; + } +} + +struct collect_diff_cbdata { + struct diff_ranges *diff; +}; + +static int collect_diff_cb(long start_a, long count_a, + long start_b, long count_b, + void *data) +{ + struct collect_diff_cbdata *d = data; + + if (count_a >= 0) + range_set_append(&d->diff->parent, start_a, start_a + count_a); + if (count_b >= 0) + range_set_append(&d->diff->target, start_b, start_b + count_b); + + return 0; +} + +static void collect_diff(mmfile_t *parent, mmfile_t *target, struct diff_ranges *out) +{ + struct collect_diff_cbdata cbdata = {NULL}; + xpparam_t xpp; + xdemitconf_t xecfg; + xdemitcb_t ecb; + + memset(&xpp, 0, sizeof(xpp)); + memset(&xecfg, 0, sizeof(xecfg)); + xecfg.ctxlen = xecfg.interhunkctxlen = 0; + + cbdata.diff = out; + xecfg.hunk_func = collect_diff_cb; + memset(&ecb, 0, sizeof(ecb)); + ecb.priv = &cbdata; + xdi_diff(parent, target, &xpp, &xecfg, &ecb); +} + +/* + * These are handy for debugging. Removing them with #if 0 silences + * the "unused function" warning. + */ +#if 0 +static void dump_range_set(struct range_set *rs, const char *desc) +{ + int i; + printf("range set %s (%d items):\n", desc, rs->nr); + for (i = 0; i < rs->nr; i++) + printf("\t[%ld,%ld]\n", rs->ranges[i].start, rs->ranges[i].end); +} + +static void dump_line_log_data(struct line_log_data *r) +{ + char buf[4096]; + while (r) { + snprintf(buf, 4096, "file %s\n", r->spec->path); + dump_range_set(&r->ranges, buf); + r = r->next; + } +} + +static void dump_diff_ranges(struct diff_ranges *diff, const char *desc) +{ + int i; + assert(diff->parent.nr == diff->target.nr); + printf("diff ranges %s (%d items):\n", desc, diff->parent.nr); + printf("\tparent\ttarget\n"); + for (i = 0; i < diff->parent.nr; i++) { + printf("\t[%ld,%ld]\t[%ld,%ld]\n", + diff->parent.ranges[i].start, + diff->parent.ranges[i].end, + diff->target.ranges[i].start, + diff->target.ranges[i].end); + } +} +#endif + + +static int ranges_overlap(struct range *a, struct range *b) +{ + return !(a->end <= b->start || b->end <= a->start); +} + +/* + * Given a diff and the set of interesting ranges, determine all hunks + * of the diff which touch (overlap) at least one of the interesting + * ranges in the target. + */ +static void diff_ranges_filter_touched(struct diff_ranges *out, + struct diff_ranges *diff, + struct range_set *rs) +{ + int i, j = 0; + + assert(out->target.nr == 0); + + for (i = 0; i < diff->target.nr; i++) { + while (diff->target.ranges[i].start > rs->ranges[j].end) { + j++; + if (j == rs->nr) + return; + } + if (ranges_overlap(&diff->target.ranges[i], &rs->ranges[j])) { + range_set_append(&out->parent, + diff->parent.ranges[i].start, + diff->parent.ranges[i].end); + range_set_append(&out->target, + diff->target.ranges[i].start, + diff->target.ranges[i].end); + } + } +} + +/* + * Adjust the line counts in 'rs' to account for the lines + * added/removed in the diff. + */ +static void range_set_shift_diff(struct range_set *out, + struct range_set *rs, + struct diff_ranges *diff) +{ + int i, j = 0; + long offset = 0; + struct range *src = rs->ranges; + struct range *target = diff->target.ranges; + struct range *parent = diff->parent.ranges; + + for (i = 0; i < rs->nr; i++) { + while (j < diff->target.nr && src[i].start >= target[j].start) { + offset += (parent[j].end-parent[j].start) + - (target[j].end-target[j].start); + j++; + } + range_set_append(out, src[i].start+offset, src[i].end+offset); + } +} + +/* + * Given a diff and the set of interesting ranges, map the ranges + * across the diff. That is: observe that the target commit takes + * blame for all the + (target-side) ranges. So for every pair of + * ranges in the diff that was touched, we remove the latter and add + * its parent side. + */ +static void range_set_map_across_diff(struct range_set *out, + struct range_set *rs, + struct diff_ranges *diff, + struct diff_ranges **touched_out) +{ + struct diff_ranges *touched = xmalloc(sizeof(*touched)); + struct range_set tmp1 = RANGE_SET_INIT; + struct range_set tmp2 = RANGE_SET_INIT; + + diff_ranges_init(touched); + diff_ranges_filter_touched(touched, diff, rs); + range_set_difference(&tmp1, rs, &touched->target); + range_set_shift_diff(&tmp2, &tmp1, diff); + range_set_union(out, &tmp2, &touched->parent); + range_set_release(&tmp1); + range_set_release(&tmp2); + + *touched_out = touched; +} + + +static struct commit *check_single_commit(struct rev_info *revs) +{ + struct object *commit = NULL; + int found = -1; + int i; + + for (i = 0; i < revs->pending.nr; i++) { + struct object *obj = revs->pending.objects[i].item; + if (obj->flags & UNINTERESTING) + continue; + while (obj->type == OBJ_TAG) + obj = deref_tag(obj, NULL, 0); + if (obj->type != OBJ_COMMIT) + die("Non commit %s?", revs->pending.objects[i].name); + if (commit) + die("More than one commit to dig from: %s and %s?", + revs->pending.objects[i].name, + revs->pending.objects[found].name); + commit = obj; + found = i; + } + + if (!commit) + die("No commit specified?"); + + return (struct commit *) commit; +} + +static void fill_blob_sha1(struct commit *commit, struct diff_filespec *spec) +{ + unsigned mode; + unsigned char sha1[20]; + + if (get_tree_entry(commit->object.sha1, spec->path, + sha1, &mode)) + die("There is no path %s in the commit", spec->path); + fill_filespec(spec, sha1, 1, mode); + + return; +} + +static void fill_line_ends(struct diff_filespec *spec, long *lines, + unsigned long **line_ends) +{ + int num = 0, size = 50; + long cur = 0; + unsigned long *ends = NULL; + char *data = NULL; + + if (diff_populate_filespec(spec, 0)) + die("Cannot read blob %s", sha1_to_hex(spec->sha1)); + + ends = xmalloc(size * sizeof(*ends)); + ends[cur++] = 0; + data = spec->data; + while (num < spec->size) { + if (data[num] == '\n' || num == spec->size - 1) { + ALLOC_GROW(ends, (cur + 1), size); + ends[cur++] = num; + } + num++; + } + + /* shrink the array to fit the elements */ + ends = xrealloc(ends, cur * sizeof(*ends)); + *lines = cur-1; + *line_ends = ends; +} + +struct nth_line_cb { + struct diff_filespec *spec; + long lines; + unsigned long *line_ends; +}; + +static const char *nth_line(void *data, long line) +{ + struct nth_line_cb *d = data; + assert(d && line <= d->lines); + assert(d->spec && d->spec->data); + + if (line == 0) + return (char *)d->spec->data; + else + return (char *)d->spec->data + d->line_ends[line] + 1; +} + +static struct line_log_data * +parse_lines(struct commit *commit, const char *prefix, struct string_list *args) +{ + long lines = 0; + unsigned long *ends = NULL; + struct nth_line_cb cb_data; + struct string_list_item *item; + struct line_log_data *ranges = NULL; + + for_each_string_list_item(item, args) { + const char *name_part, *range_part; + const char *full_name; + struct diff_filespec *spec; + long begin = 0, end = 0; + + name_part = skip_range_arg(item->string); + if (!name_part || *name_part != ':' || !name_part[1]) + die("-L argument '%s' not of the form start,end:file", + item->string); + range_part = xstrndup(item->string, name_part - item->string); + name_part++; + + full_name = prefix_path(prefix, prefix ? strlen(prefix) : 0, + name_part); + + spec = alloc_filespec(full_name); + fill_blob_sha1(commit, spec); + fill_line_ends(spec, &lines, &ends); + cb_data.spec = spec; + cb_data.lines = lines; + cb_data.line_ends = ends; + + if (parse_range_arg(range_part, nth_line, &cb_data, + lines, &begin, &end)) + die("malformed -L argument '%s'", range_part); + if (begin < 1) + begin = 1; + if (end < 1) + end = lines; + begin--; + if (lines < end || lines < begin) + die("file %s has only %ld lines", name_part, lines); + line_log_data_insert(&ranges, spec, begin, end); + + free(ends); + ends = NULL; + } + + return ranges; +} + +static struct line_log_data *line_log_data_copy_one(struct line_log_data *r) +{ + struct line_log_data *ret = xmalloc(sizeof(*ret)); + + assert(r); + line_log_data_init(ret); + range_set_copy(&ret->ranges, &r->ranges); + + ret->spec = r->spec; + assert(ret->spec); + ret->spec->count++; + + return ret; +} + +static struct line_log_data * +line_log_data_copy(struct line_log_data *r) +{ + struct line_log_data *ret = NULL; + struct line_log_data *tmp = NULL, *prev = NULL; + + assert(r); + ret = tmp = prev = line_log_data_copy_one(r); + r = r->next; + while (r) { + tmp = line_log_data_copy_one(r); + prev->next = tmp; + prev = tmp; + r = r->next; + } + + return ret; +} + +/* merge two range sets across files */ +static struct line_log_data *line_log_data_merge(struct line_log_data *a, + struct line_log_data *b) +{ + struct line_log_data *head = NULL, **pp = &head; + + while (a || b) { + struct line_log_data *src; + struct line_log_data *src2 = NULL; + struct line_log_data *d; + int cmp; + if (!a) + cmp = 1; + else if (!b) + cmp = -1; + else + cmp = strcmp(a->spec->path, b->spec->path); + if (cmp < 0) { + src = a; + a = a->next; + } else if (cmp == 0) { + src = a; + a = a->next; + src2 = b; + b = b->next; + } else { + src = b; + b = b->next; + } + d = xmalloc(sizeof(struct line_log_data)); + line_log_data_init(d); + d->spec = src->spec; + d->spec->count++; + *pp = d; + pp = &d->next; + if (src2) + range_set_union(&d->ranges, &src->ranges, &src2->ranges); + else + range_set_copy(&d->ranges, &src->ranges); + } + + return head; +} + +static void add_line_range(struct rev_info *revs, struct commit *commit, + struct line_log_data *range) +{ + struct line_log_data *old = NULL; + struct line_log_data *new = NULL; + + old = lookup_decoration(&revs->line_log_data, &commit->object); + if (old && range) { + new = line_log_data_merge(old, range); + free_line_log_data(old); + } else if (range) + new = line_log_data_copy(range); + + if (new) + add_decoration(&revs->line_log_data, &commit->object, new); +} + +static void clear_commit_line_range(struct rev_info *revs, struct commit *commit) +{ + struct line_log_data *r; + r = lookup_decoration(&revs->line_log_data, &commit->object); + if (!r) + return; + free_line_log_data(r); + add_decoration(&revs->line_log_data, &commit->object, NULL); +} + +static struct line_log_data *lookup_line_range(struct rev_info *revs, + struct commit *commit) +{ + struct line_log_data *ret = NULL; + + ret = lookup_decoration(&revs->line_log_data, &commit->object); + return ret; +} + +void line_log_init(struct rev_info *rev, const char *prefix, struct string_list *args) +{ + struct commit *commit = NULL; + struct line_log_data *range; + + commit = check_single_commit(rev); + range = parse_lines(commit, prefix, args); + add_line_range(rev, commit, range); + + if (!rev->diffopt.detect_rename) { + int i, count = 0; + struct line_log_data *r = range; + const char **paths; + while (r) { + count++; + r = r->next; + } + paths = xmalloc((count+1)*sizeof(char *)); + r = range; + for (i = 0; i < count; i++) { + paths[i] = xstrdup(r->spec->path); + r = r->next; + } + paths[count] = NULL; + init_pathspec(&rev->diffopt.pathspec, paths); + free(paths); + } +} + +static void load_tree_desc(struct tree_desc *desc, void **tree, + const unsigned char *sha1) +{ + unsigned long size; + *tree = read_object_with_reference(sha1, tree_type, &size, NULL); + if (!*tree) + die("Unable to read tree (%s)", sha1_to_hex(sha1)); + init_tree_desc(desc, *tree, size); +} + +static int count_parents(struct commit *commit) +{ + struct commit_list *parents = commit->parents; + int count = 0; + while (parents) { + count++; + parents = parents->next; + } + return count; +} + +static void move_diff_queue(struct diff_queue_struct *dst, + struct diff_queue_struct *src) +{ + assert(src != dst); + memcpy(dst, src, sizeof(struct diff_queue_struct)); + DIFF_QUEUE_CLEAR(src); +} + +static void queue_diffs(struct diff_options *opt, + struct diff_queue_struct *queue, + struct commit *commit, struct commit *parent) +{ + void *tree1 = NULL, *tree2 = NULL; + struct tree_desc desc1, desc2; + + assert(commit); + load_tree_desc(&desc2, &tree2, commit->tree->object.sha1); + if (parent) + load_tree_desc(&desc1, &tree1, parent->tree->object.sha1); + else + init_tree_desc(&desc1, "", 0); + + DIFF_QUEUE_CLEAR(&diff_queued_diff); + diff_tree(&desc1, &desc2, "", opt); + diffcore_std(opt); + move_diff_queue(queue, &diff_queued_diff); + + if (tree1) + free(tree1); + if (tree2) + free(tree2); +} + +static char *get_nth_line(long line, unsigned long *ends, void *data) +{ + if (line == 0) + return (char *)data; + else + return (char *)data + ends[line] + 1; +} + +static void print_line(const char *prefix, char first, + long line, unsigned long *ends, void *data, + const char *color, const char *reset) +{ + char *begin = get_nth_line(line, ends, data); + char *end = get_nth_line(line+1, ends, data); + int had_nl = 0; + + if (end > begin && end[-1] == '\n') { + end--; + had_nl = 1; + } + + fputs(prefix, stdout); + fputs(color, stdout); + putchar(first); + fwrite(begin, 1, end-begin, stdout); + fputs(reset, stdout); + putchar('\n'); + if (!had_nl) + fputs("\\ No newline at end of file\n", stdout); +} + +static char *output_prefix(struct diff_options *opt) +{ + char *prefix = ""; + + if (opt->output_prefix) { + struct strbuf *sb = opt->output_prefix(opt, opt->output_prefix_data); + prefix = sb->buf; + } + + return prefix; +} + +static void dump_diff_hacky_one(struct rev_info *rev, struct line_log_data *range) +{ + int i, j = 0; + long p_lines, t_lines; + unsigned long *p_ends = NULL, *t_ends = NULL; + struct diff_filepair *pair = range->pair; + struct diff_ranges *diff = &range->diff; + + struct diff_options *opt = &rev->diffopt; + char *prefix = output_prefix(opt); + const char *c_reset = diff_get_color(opt->use_color, DIFF_RESET); + const char *c_frag = diff_get_color(opt->use_color, DIFF_FRAGINFO); + const char *c_meta = diff_get_color(opt->use_color, DIFF_METAINFO); + const char *c_old = diff_get_color(opt->use_color, DIFF_FILE_OLD); + const char *c_new = diff_get_color(opt->use_color, DIFF_FILE_NEW); + const char *c_plain = diff_get_color(opt->use_color, DIFF_PLAIN); + + if (!pair || !diff) + return; + + if (pair->one->sha1_valid) + fill_line_ends(pair->one, &p_lines, &p_ends); + fill_line_ends(pair->two, &t_lines, &t_ends); + + printf("%s%sdiff --git a/%s b/%s%s\n", prefix, c_meta, pair->one->path, pair->two->path, c_reset); + printf("%s%s--- %s%s%s\n", prefix, c_meta, + pair->one->sha1_valid ? "a/" : "", + pair->one->sha1_valid ? pair->one->path : "/dev/null", + c_reset); + printf("%s%s+++ b/%s%s\n", prefix, c_meta, pair->two->path, c_reset); + for (i = 0; i < range->ranges.nr; i++) { + long p_start, p_end; + long t_start = range->ranges.ranges[i].start; + long t_end = range->ranges.ranges[i].end; + long t_cur = t_start; + int j_last; + + while (j < diff->target.nr && diff->target.ranges[j].end < t_start) + j++; + if (j == diff->target.nr || diff->target.ranges[j].start > t_end) + continue; + + /* Scan ahead to determine the last diff that falls in this range */ + j_last = j; + while (j_last < diff->target.nr && diff->target.ranges[j_last].start < t_end) + j_last++; + if (j_last > j) + j_last--; + + /* + * Compute parent hunk headers: we know that the diff + * has the correct line numbers (but not all hunks). + * So it suffices to shift the start/end according to + * the line numbers of the first/last hunk(s) that + * fall in this range. + */ + if (t_start < diff->target.ranges[j].start) + p_start = diff->parent.ranges[j].start - (diff->target.ranges[j].start-t_start); + else + p_start = diff->parent.ranges[j].start; + if (t_end > diff->target.ranges[j_last].end) + p_end = diff->parent.ranges[j_last].end + (t_end-diff->target.ranges[j_last].end); + else + p_end = diff->parent.ranges[j_last].end; + + if (!p_start && !p_end) { + p_start = -1; + p_end = -1; + } + + /* Now output a diff hunk for this range */ + printf("%s%s@@ -%ld,%ld +%ld,%ld @@%s\n", + prefix, c_frag, + p_start+1, p_end-p_start, t_start+1, t_end-t_start, + c_reset); + while (j < diff->target.nr && diff->target.ranges[j].start < t_end) { + int k; + for (; t_cur < diff->target.ranges[j].start; t_cur++) + print_line(prefix, ' ', t_cur, t_ends, pair->two->data, + c_plain, c_reset); + for (k = diff->parent.ranges[j].start; k < diff->parent.ranges[j].end; k++) + print_line(prefix, '-', k, p_ends, pair->one->data, + c_old, c_reset); + for (; t_cur < diff->target.ranges[j].end && t_cur < t_end; t_cur++) + print_line(prefix, '+', t_cur, t_ends, pair->two->data, + c_new, c_reset); + j++; + } + for (; t_cur < t_end; t_cur++) + print_line(prefix, ' ', t_cur, t_ends, pair->two->data, + c_plain, c_reset); + } + + free(p_ends); + free(t_ends); +} + +/* + * NEEDSWORK: manually building a diff here is not the Right + * Thing(tm). log -L should be built into the diff pipeline. + */ +static void dump_diff_hacky(struct rev_info *rev, struct line_log_data *range) +{ + puts(output_prefix(&rev->diffopt)); + while (range) { + dump_diff_hacky_one(rev, range); + range = range->next; + } +} + +/* + * Unlike most other functions, this destructively operates on + * 'range'. + */ +static int process_diff_filepair(struct rev_info *rev, + struct diff_filepair *pair, + struct line_log_data *range, + struct diff_ranges **diff_out) +{ + struct line_log_data *rg = range; + struct range_set tmp; + struct diff_ranges diff; + mmfile_t file_parent, file_target; + + assert(pair->two->path); + while (rg) { + assert(rg->spec->path); + if (!strcmp(rg->spec->path, pair->two->path)) + break; + rg = rg->next; + } + + if (!rg) + return 0; + if (rg->ranges.nr == 0) + return 0; + + assert(pair->two->sha1_valid); + diff_populate_filespec(pair->two, 0); + file_target.ptr = pair->two->data; + file_target.size = pair->two->size; + + if (pair->one->sha1_valid) { + diff_populate_filespec(pair->one, 0); + file_parent.ptr = pair->one->data; + file_parent.size = pair->one->size; + } else { + file_parent.ptr = ""; + file_parent.size = 0; + } + + diff_ranges_init(&diff); + collect_diff(&file_parent, &file_target, &diff); + + /* NEEDSWORK should apply some heuristics to prevent mismatches */ + rg->spec->path = xstrdup(pair->one->path); + + range_set_init(&tmp, 0); + range_set_map_across_diff(&tmp, &rg->ranges, &diff, diff_out); + range_set_release(&rg->ranges); + range_set_move(&rg->ranges, &tmp); + + diff_ranges_release(&diff); + + return ((*diff_out)->parent.nr > 0); +} + +static struct diff_filepair *diff_filepair_dup(struct diff_filepair *pair) +{ + struct diff_filepair *new = xmalloc(sizeof(struct diff_filepair)); + new->one = pair->one; + new->two = pair->two; + new->one->count++; + new->two->count++; + return new; +} + +static void free_diffqueues(int n, struct diff_queue_struct *dq) +{ + int i, j; + for (i = 0; i < n; i++) + for (j = 0; j < dq[i].nr; j++) + diff_free_filepair(dq[i].queue[j]); + free(dq); +} + +static int process_all_files(struct line_log_data **range_out, + struct rev_info *rev, + struct diff_queue_struct *queue, + struct line_log_data *range) +{ + int i, changed = 0; + + *range_out = line_log_data_copy(range); + + for (i = 0; i < queue->nr; i++) { + struct diff_ranges *pairdiff = NULL; + if (process_diff_filepair(rev, queue->queue[i], *range_out, &pairdiff)) { + struct line_log_data *rg = range; + changed++; + /* NEEDSWORK tramples over data structures not owned here */ + while (rg && strcmp(rg->spec->path, queue->queue[i]->two->path)) + rg = rg->next; + assert(rg); + rg->pair = diff_filepair_dup(queue->queue[i]); + memcpy(&rg->diff, pairdiff, sizeof(struct diff_ranges)); + } + } + + return changed; +} + +int line_log_print(struct rev_info *rev, struct commit *commit) +{ + struct line_log_data *range = lookup_line_range(rev, commit); + + show_log(rev); + dump_diff_hacky(rev, range); + return 1; +} + +static int process_ranges_ordinary_commit(struct rev_info *rev, struct commit *commit, + struct line_log_data *range) +{ + struct commit *parent = NULL; + struct diff_queue_struct queue; + struct line_log_data *parent_range; + int changed; + + if (commit->parents) + parent = commit->parents->item; + + queue_diffs(&rev->diffopt, &queue, commit, parent); + changed = process_all_files(&parent_range, rev, &queue, range); + if (parent) + add_line_range(rev, parent, parent_range); + return changed; +} + +static int process_ranges_merge_commit(struct rev_info *rev, struct commit *commit, + struct line_log_data *range) +{ + struct diff_queue_struct *diffqueues; + struct line_log_data **cand; + struct commit **parents; + struct commit_list *p; + int i; + int nparents = count_parents(commit); + + diffqueues = xmalloc(nparents * sizeof(*diffqueues)); + cand = xmalloc(nparents * sizeof(*cand)); + parents = xmalloc(nparents * sizeof(*parents)); + + p = commit->parents; + for (i = 0; i < nparents; i++) { + parents[i] = p->item; + p = p->next; + queue_diffs(&rev->diffopt, &diffqueues[i], commit, parents[i]); + } + + for (i = 0; i < nparents; i++) { + int changed; + cand[i] = NULL; + changed = process_all_files(&cand[i], rev, &diffqueues[i], range); + if (!changed) { + /* + * This parent can take all the blame, so we + * don't follow any other path in history + */ + add_line_range(rev, parents[i], cand[i]); + clear_commit_line_range(rev, commit); + commit->parents = xmalloc(sizeof(struct commit_list)); + commit->parents->item = parents[i]; + commit->parents->next = NULL; + free(parents); + free(cand); + free_diffqueues(nparents, diffqueues); + /* NEEDSWORK leaking like a sieve */ + return 0; + } + } + + /* + * No single parent took the blame. We add the candidates + * from the above loop to the parents. + */ + for (i = 0; i < nparents; i++) { + add_line_range(rev, parents[i], cand[i]); + } + + clear_commit_line_range(rev, commit); + free(parents); + free(cand); + free_diffqueues(nparents, diffqueues); + return 1; + + /* NEEDSWORK evil merge detection stuff */ + /* NEEDSWORK leaking like a sieve */ +} + +static int process_ranges_arbitrary_commit(struct rev_info *rev, struct commit *commit) +{ + struct line_log_data *range = lookup_line_range(rev, commit); + int changed = 0; + + if (range) { + if (!commit->parents || !commit->parents->next) + changed = process_ranges_ordinary_commit(rev, commit, range); + else + changed = process_ranges_merge_commit(rev, commit, range); + } + + if (!changed) + commit->object.flags |= TREESAME; + + return changed; +} + +static enum rewrite_result line_log_rewrite_one(struct rev_info *rev, struct commit **pp) +{ + for (;;) { + struct commit *p = *pp; + if (p->parents && p->parents->next) + return rewrite_one_ok; + if (p->object.flags & UNINTERESTING) + return rewrite_one_ok; + if (!(p->object.flags & TREESAME)) + return rewrite_one_ok; + if (!p->parents) + return rewrite_one_noparents; + *pp = p->parents->item; + } +} + +int line_log_filter(struct rev_info *rev) +{ + struct commit *commit; + struct commit_list *list = rev->commits; + struct commit_list *out = NULL, **pp = &out; + + while (list) { + struct commit_list *to_free = NULL; + commit = list->item; + if (process_ranges_arbitrary_commit(rev, commit)) { + *pp = list; + pp = &list->next; + } else + to_free = list; + list = list->next; + free(to_free); + } + *pp = NULL; + + for (list = out; list; list = list->next) + rewrite_parents(rev, list->item, line_log_rewrite_one); + + rev->commits = out; + + return 0; +} diff --git a/line-log.h b/line-log.h new file mode 100644 index 0000000000..9acd12361a --- /dev/null +++ b/line-log.h @@ -0,0 +1,49 @@ +#ifndef LINE_LOG_H +#define LINE_LOG_H + +#include "diffcore.h" + +struct rev_info; +struct commit; + +/* A range [start,end]. Lines are numbered starting at 0, and the + * ranges include start but exclude end. */ +struct range { + long start, end; +}; + +/* A set of ranges. The ranges must always be disjoint and sorted. */ +struct range_set { + int alloc, nr; + struct range *ranges; +}; + +/* A diff, encoded as the set of pre- and post-image ranges where the + * files differ. A pair of ranges corresponds to a hunk. */ +struct diff_ranges { + struct range_set parent; + struct range_set target; +}; + +/* Linked list of interesting files and their associated ranges. The + * list must be kept sorted by spec->path */ +struct line_log_data { + struct line_log_data *next; + struct diff_filespec *spec; + char status; + struct range_set ranges; + int arg_alloc, arg_nr; + const char **args; + struct diff_filepair *pair; + struct diff_ranges diff; +}; + +extern void line_log_data_init(struct line_log_data *r); + +extern void line_log_init(struct rev_info *rev, const char *prefix, struct string_list *args); + +extern int line_log_filter(struct rev_info *rev); + +extern int line_log_print(struct rev_info *rev, struct commit *commit); + +#endif /* LINE_LOG_H */ diff --git a/line-range.c b/line-range.c index 5a226abdd0..7a7ca3c2bd 100644 --- a/line-range.c +++ b/line-range.c @@ -21,6 +21,8 @@ static const char *parse_loc(const char *spec, nth_line_fn_t nth_line, if (1 < begin && (spec[0] == '+' || spec[0] == '-')) { num = strtol(spec + 1, &term, 10); if (term != spec + 1) { + if (!ret) + return term; if (spec[0] == '-') num = 0 - num; if (0 < num) @@ -35,7 +37,8 @@ static const char *parse_loc(const char *spec, nth_line_fn_t nth_line, } num = strtol(spec, &term, 10); if (term != spec) { - *ret = num; + if (ret) + *ret = num; return term; } if (spec[0] != '/') @@ -49,6 +52,10 @@ static const char *parse_loc(const char *spec, nth_line_fn_t nth_line, if (*term != '/') return spec; + /* in the scan-only case we are not interested in the regex */ + if (!ret) + return term+1; + /* try [spec+1 .. term-1] as regexp */ *term = 0; begin--; /* input is in human terms */ @@ -90,3 +97,13 @@ int parse_range_arg(const char *arg, nth_line_fn_t nth_line_cb, return 0; } + +const char *skip_range_arg(const char *arg) +{ + arg = parse_loc(arg, NULL, NULL, 0, -1, NULL); + + if (*arg == ',') + arg = parse_loc(arg+1, NULL, NULL, 0, 0, NULL); + + return arg; +} diff --git a/line-range.h b/line-range.h index 830f25b501..88aaf08b7f 100644 --- a/line-range.h +++ b/line-range.h @@ -21,4 +21,15 @@ extern int parse_range_arg(const char *arg, void *cb_data, long lines, long *begin, long *end); +/* + * Scan past a range argument that could be parsed by + * 'parse_range_arg', to help the caller determine the start of the + * filename in '-L n,m:file' syntax. + * + * Returns a pointer to the first character after the 'n,m' part, or + * NULL in case the argument is obviously malformed. + */ + +extern const char *skip_range_arg(const char *arg); + #endif /* LINE_RANGE_H */ diff --git a/log-tree.c b/log-tree.c index 5dc45c4812..793d2c8e99 100644 --- a/log-tree.c +++ b/log-tree.c @@ -9,6 +9,7 @@ #include "string-list.h" #include "color.h" #include "gpg-interface.h" +#include "line-log.h" struct decoration name_decoration = { "object names" }; @@ -856,6 +857,9 @@ int log_tree_commit(struct rev_info *opt, struct commit *commit) log.parent = NULL; opt->loginfo = &log; + if (opt->line_level_traverse) + return line_log_print(opt, commit); + shown = log_tree_diff(opt, commit, &log); if (!shown && opt->loginfo && opt->always_show_header) { log.parent = NULL; diff --git a/revision.c b/revision.c index 46319d52b4..3ad9d08c7f 100644 --- a/revision.c +++ b/revision.c @@ -13,6 +13,7 @@ #include "decorate.h" #include "log-tree.h" #include "string-list.h" +#include "line-log.h" #include "mailmap.h" volatile show_early_output_fn_t show_early_output; @@ -1896,6 +1897,12 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s if (revs->combine_merges) revs->ignore_merges = 0; revs->diffopt.abbrev = revs->abbrev; + + if (revs->line_level_traverse) { + revs->limited = 1; + revs->topo_order = 1; + } + diff_setup_done(&revs->diffopt); grep_commit_pattern_type(GREP_PATTERN_TYPE_UNSPECIFIED, @@ -2166,6 +2173,8 @@ int prepare_revision_walk(struct rev_info *revs) return -1; if (revs->topo_order) sort_in_topological_order(&revs->commits, revs->lifo); + if (revs->line_level_traverse) + line_log_filter(revs); if (revs->simplify_merges) simplify_merges(revs); if (revs->children.name) diff --git a/revision.h b/revision.h index 640110d73e..6b2870ca10 100644 --- a/revision.h +++ b/revision.h @@ -96,7 +96,8 @@ struct rev_info { cherry_mark:1, bisect:1, ancestry_path:1, - first_parent_only:1; + first_parent_only:1, + line_level_traverse:1; /* Diff flags */ unsigned int diff:1, @@ -175,6 +176,9 @@ struct rev_info { int count_left; int count_right; int count_same; + + /* line level range that we are chasing */ + struct decoration line_log_data; }; #define REV_TREE_SAME 0 diff --git a/t/perf/p4211-line-log.sh b/t/perf/p4211-line-log.sh new file mode 100755 index 0000000000..3d074b0e41 --- /dev/null +++ b/t/perf/p4211-line-log.sh @@ -0,0 +1,34 @@ +#!/bin/sh + +test_description='Tests log -L performance' +. ./perf-lib.sh + +test_perf_default_repo + +# Pick a file to log pseudo-randomly. The sort key is the blob hash, +# so it is stable. +test_expect_success 'select a file' ' + git ls-tree HEAD | grep ^100644 | + sort -k 3 | head -1 | cut -f 2 >filelist +' + +file=$(cat filelist) +export file + +test_perf 'git rev-list --topo-order (baseline)' ' + git rev-list --topo-order HEAD >/dev/null +' + +test_perf 'git log --follow (baseline for -M)' ' + git log --oneline --follow -- "$file" >/dev/null +' + +test_perf 'git log -L' ' + git log -L 1:"$file" >/dev/null +' + +test_perf 'git log -M -L' ' + git log -M -L 1:"$file" >/dev/null +' + +test_done diff --git a/t/t4211-line-log.sh b/t/t4211-line-log.sh new file mode 100755 index 0000000000..9f36f17384 --- /dev/null +++ b/t/t4211-line-log.sh @@ -0,0 +1,49 @@ +#!/bin/sh + +test_description='test log -L' +. ./test-lib.sh + +test_expect_success 'setup (import history)' ' + git fast-import < "$TEST_DIRECTORY"/t4211/history.export && + git reset --hard +' + +canned_test () { + test_expect_success "$1" " + git log $1 >actual && + test_cmp \"\$TEST_DIRECTORY\"/t4211/expect.$2 actual + " +} + +test_bad_opts () { + test_expect_success "invalid args: $1" " + test_must_fail git log $1 2>errors && + grep '$2' errors + " +} + +canned_test "-L 4,12:a.c simple" simple-f +canned_test "-L 4,+9:a.c simple" simple-f +canned_test "-L '/long f/,/^}/:a.c' simple" simple-f + +canned_test "-L '/main/,/^}/:a.c' simple" simple-main + +canned_test "-L 1,+4:a.c simple" beginning-of-file + +canned_test "-L 20:a.c simple" end-of-file + +canned_test "-L '/long f/',/^}/:a.c -L /main/,/^}/:a.c simple" two-ranges +canned_test "-L 24,+1:a.c simple" vanishes-early + +canned_test "-L '/long f/,/^}/:b.c' move-support" move-support-f + +test_bad_opts "-L" "switch.*requires a value" +test_bad_opts "-L b.c" "argument.*not of the form" +test_bad_opts "-L 1:" "argument.*not of the form" +test_bad_opts "-L 1:nonexistent" "There is no path" +test_bad_opts "-L 1:simple" "There is no path" +test_bad_opts "-L '/foo:b.c'" "argument.*not of the form" +test_bad_opts "-L 1000:b.c" "has only.*lines" +test_bad_opts "-L 1,1000:b.c" "has only.*lines" + +test_done diff --git a/t/t4211/expect.beginning-of-file b/t/t4211/expect.beginning-of-file new file mode 100644 index 0000000000..91b4054898 --- /dev/null +++ b/t/t4211/expect.beginning-of-file @@ -0,0 +1,43 @@ +commit 4a23ae5c98d59a58c6da036156959f2dc9f472ad +Author: Thomas Rast +Date: Thu Feb 28 10:47:40 2013 +0100 + + change at very beginning + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -1,3 +1,4 @@ ++#include + #include + + long f(long x) + +commit a6eb82647d5d67f893da442f8f9375fd89a3b1e2 +Author: Thomas Rast +Date: Thu Feb 28 10:45:16 2013 +0100 + + touch both functions + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -1,3 +1,3 @@ + #include + +-int f(int x) ++long f(long x) + +commit de4c48ae814792c02a49c4c3c0c757ae69c55f6a +Author: Thomas Rast +Date: Thu Feb 28 10:44:48 2013 +0100 + + initial + +diff --git a/a.c b/a.c +--- /dev/null ++++ b/a.c +@@ -0,0 +1,3 @@ ++#include ++ ++int f(int x) diff --git a/t/t4211/expect.end-of-file b/t/t4211/expect.end-of-file new file mode 100644 index 0000000000..bd25bb2f59 --- /dev/null +++ b/t/t4211/expect.end-of-file @@ -0,0 +1,62 @@ +commit 4659538844daa2849b1a9e7d6fadb96fcd26fc83 +Author: Thomas Rast +Date: Thu Feb 28 10:48:43 2013 +0100 + + change back to complete line + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -20,3 +20,5 @@ + printf("%ld\n", f(15)); + return 0; +-} +\ No newline at end of file ++} ++ ++/* incomplete lines are bad! */ + +commit 100b61a6f2f720f812620a9d10afb3a960ccb73c +Author: Thomas Rast +Date: Thu Feb 28 10:48:10 2013 +0100 + + change to an incomplete line at end + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -20,3 +20,3 @@ + printf("%ld\n", f(15)); + return 0; +-} ++} +\ No newline at end of file + +commit a6eb82647d5d67f893da442f8f9375fd89a3b1e2 +Author: Thomas Rast +Date: Thu Feb 28 10:45:16 2013 +0100 + + touch both functions + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -19,3 +19,3 @@ +- printf("%d\n", f(15)); ++ printf("%ld\n", f(15)); + return 0; + } + +commit de4c48ae814792c02a49c4c3c0c757ae69c55f6a +Author: Thomas Rast +Date: Thu Feb 28 10:44:48 2013 +0100 + + initial + +diff --git a/a.c b/a.c +--- /dev/null ++++ b/a.c +@@ -0,0 +18,3 @@ ++ printf("%d\n", f(15)); ++ return 0; ++} diff --git a/t/t4211/expect.move-support-f b/t/t4211/expect.move-support-f new file mode 100644 index 0000000000..78a8cf1afd --- /dev/null +++ b/t/t4211/expect.move-support-f @@ -0,0 +1,40 @@ +commit 6ce3c4ff690136099bb17e1a8766b75764726ea7 +Author: Thomas Rast +Date: Thu Feb 28 10:49:50 2013 +0100 + + another simple change + +diff --git a/b.c b/b.c +--- a/b.c ++++ b/b.c +@@ -4,9 +4,9 @@ + long f(long x) + { + int s = 0; + while (x) { +- x >>= 1; ++ x /= 2; + s++; + } + return s; + } + +commit e6da343666244ea9e67cbe3f3bd26da860f9fe0e +Author: Thomas Rast +Date: Thu Feb 28 10:49:28 2013 +0100 + + move file + +diff --git a/b.c b/b.c +--- /dev/null ++++ b/b.c +@@ -0,0 +4,9 @@ ++long f(long x) ++{ ++ int s = 0; ++ while (x) { ++ x >>= 1; ++ s++; ++ } ++ return s; ++} diff --git a/t/t4211/expect.simple-f b/t/t4211/expect.simple-f new file mode 100644 index 0000000000..a1f5bc49c8 --- /dev/null +++ b/t/t4211/expect.simple-f @@ -0,0 +1,59 @@ +commit a6eb82647d5d67f893da442f8f9375fd89a3b1e2 +Author: Thomas Rast +Date: Thu Feb 28 10:45:16 2013 +0100 + + touch both functions + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,9 +3,9 @@ +-int f(int x) ++long f(long x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; + } + +commit f04fb20f2c77850996cba739709acc6faecc58f7 +Author: Thomas Rast +Date: Thu Feb 28 10:44:55 2013 +0100 + + change f() + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,8 +3,9 @@ + int f(int x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } ++ return s; + } + +commit de4c48ae814792c02a49c4c3c0c757ae69c55f6a +Author: Thomas Rast +Date: Thu Feb 28 10:44:48 2013 +0100 + + initial + +diff --git a/a.c b/a.c +--- /dev/null ++++ b/a.c +@@ -0,0 +3,8 @@ ++int f(int x) ++{ ++ int s = 0; ++ while (x) { ++ x >>= 1; ++ s++; ++ } ++} diff --git a/t/t4211/expect.simple-main b/t/t4211/expect.simple-main new file mode 100644 index 0000000000..39ce39bebe --- /dev/null +++ b/t/t4211/expect.simple-main @@ -0,0 +1,68 @@ +commit 4659538844daa2849b1a9e7d6fadb96fcd26fc83 +Author: Thomas Rast +Date: Thu Feb 28 10:48:43 2013 +0100 + + change back to complete line + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -18,5 +18,5 @@ + int main () + { + printf("%ld\n", f(15)); + return 0; +-} +\ No newline at end of file ++} + +commit 100b61a6f2f720f812620a9d10afb3a960ccb73c +Author: Thomas Rast +Date: Thu Feb 28 10:48:10 2013 +0100 + + change to an incomplete line at end + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -18,5 +18,5 @@ + int main () + { + printf("%ld\n", f(15)); + return 0; +-} ++} +\ No newline at end of file + +commit a6eb82647d5d67f893da442f8f9375fd89a3b1e2 +Author: Thomas Rast +Date: Thu Feb 28 10:45:16 2013 +0100 + + touch both functions + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -17,5 +17,5 @@ + int main () + { +- printf("%d\n", f(15)); ++ printf("%ld\n", f(15)); + return 0; + } + +commit de4c48ae814792c02a49c4c3c0c757ae69c55f6a +Author: Thomas Rast +Date: Thu Feb 28 10:44:48 2013 +0100 + + initial + +diff --git a/a.c b/a.c +--- /dev/null ++++ b/a.c +@@ -0,0 +16,5 @@ ++int main () ++{ ++ printf("%d\n", f(15)); ++ return 0; ++} diff --git a/t/t4211/expect.two-ranges b/t/t4211/expect.two-ranges new file mode 100644 index 0000000000..6109aa0dce --- /dev/null +++ b/t/t4211/expect.two-ranges @@ -0,0 +1,102 @@ +commit 4659538844daa2849b1a9e7d6fadb96fcd26fc83 +Author: Thomas Rast +Date: Thu Feb 28 10:48:43 2013 +0100 + + change back to complete line + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -18,5 +18,5 @@ + int main () + { + printf("%ld\n", f(15)); + return 0; +-} +\ No newline at end of file ++} + +commit 100b61a6f2f720f812620a9d10afb3a960ccb73c +Author: Thomas Rast +Date: Thu Feb 28 10:48:10 2013 +0100 + + change to an incomplete line at end + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -18,5 +18,5 @@ + int main () + { + printf("%ld\n", f(15)); + return 0; +-} ++} +\ No newline at end of file + +commit a6eb82647d5d67f893da442f8f9375fd89a3b1e2 +Author: Thomas Rast +Date: Thu Feb 28 10:45:16 2013 +0100 + + touch both functions + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,9 +3,9 @@ +-int f(int x) ++long f(long x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; + } +@@ -17,5 +17,5 @@ + int main () + { +- printf("%d\n", f(15)); ++ printf("%ld\n", f(15)); + return 0; + } + +commit f04fb20f2c77850996cba739709acc6faecc58f7 +Author: Thomas Rast +Date: Thu Feb 28 10:44:55 2013 +0100 + + change f() + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,8 +3,9 @@ + int f(int x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } ++ return s; + } + +commit de4c48ae814792c02a49c4c3c0c757ae69c55f6a +Author: Thomas Rast +Date: Thu Feb 28 10:44:48 2013 +0100 + + initial + +diff --git a/a.c b/a.c +--- /dev/null ++++ b/a.c +@@ -0,0 +3,8 @@ ++int f(int x) ++{ ++ int s = 0; ++ while (x) { ++ x >>= 1; ++ s++; ++ } ++} diff --git a/t/t4211/expect.vanishes-early b/t/t4211/expect.vanishes-early new file mode 100644 index 0000000000..1f7cd06941 --- /dev/null +++ b/t/t4211/expect.vanishes-early @@ -0,0 +1,39 @@ +commit 4659538844daa2849b1a9e7d6fadb96fcd26fc83 +Author: Thomas Rast +Date: Thu Feb 28 10:48:43 2013 +0100 + + change back to complete line + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -22,1 +24,1 @@ +-} +\ No newline at end of file ++/* incomplete lines are bad! */ + +commit 100b61a6f2f720f812620a9d10afb3a960ccb73c +Author: Thomas Rast +Date: Thu Feb 28 10:48:10 2013 +0100 + + change to an incomplete line at end + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -22,1 +22,1 @@ +-} ++} +\ No newline at end of file + +commit de4c48ae814792c02a49c4c3c0c757ae69c55f6a +Author: Thomas Rast +Date: Thu Feb 28 10:44:48 2013 +0100 + + initial + +diff --git a/a.c b/a.c +--- /dev/null ++++ b/a.c +@@ -0,0 +20,1 @@ ++} diff --git a/t/t4211/history.export b/t/t4211/history.export new file mode 100644 index 0000000000..c159794740 --- /dev/null +++ b/t/t4211/history.export @@ -0,0 +1,330 @@ +blob +mark :1 +data 157 +#include + +int f(int x) +{ + int s = 0; + while (x) { + x >>= 1; + s++; + } +} + +/* + * A comment. + */ + +int main () +{ + printf("%d\n", f(15)); + return 0; +} + +reset refs/tags/simple +commit refs/tags/simple +mark :2 +author Thomas Rast 1362044688 +0100 +committer Thomas Rast 1362044688 +0100 +data 8 +initial +M 100644 :1 a.c + +blob +mark :3 +data 168 +#include + +int f(int x) +{ + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; +} + +/* + * A comment. + */ + +int main () +{ + printf("%d\n", f(15)); + return 0; +} + +commit refs/tags/simple +mark :4 +author Thomas Rast 1362044695 +0100 +committer Thomas Rast 1362044695 +0100 +data 11 +change f() +from :2 +M 100644 :3 a.c + +blob +mark :5 +data 171 +#include + +long f(long x) +{ + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; +} + +/* + * A comment. + */ + +int main () +{ + printf("%ld\n", f(15)); + return 0; +} + +commit refs/tags/simple +mark :6 +author Thomas Rast 1362044716 +0100 +committer Thomas Rast 1362044716 +0100 +data 21 +touch both functions +from :4 +M 100644 :5 a.c + +blob +mark :7 +data 185 +#include + +long f(long x) +{ + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; +} + +/* + * This is only an example! + */ + +int main () +{ + printf("%ld\n", f(15)); + return 0; +} + +commit refs/tags/simple +mark :8 +author Thomas Rast 1362044741 +0100 +committer Thomas Rast 1362044741 +0100 +data 14 +touch comment +from :6 +M 100644 :7 a.c + +blob +mark :9 +data 205 +#include +#include + +long f(long x) +{ + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; +} + +/* + * This is only an example! + */ + +int main () +{ + printf("%ld\n", f(15)); + return 0; +} + +commit refs/tags/simple +mark :10 +author Thomas Rast 1362044860 +0100 +committer Thomas Rast 1362044860 +0100 +data 25 +change at very beginning +from :8 +M 100644 :9 a.c + +blob +mark :11 +data 204 +#include +#include + +long f(long x) +{ + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; +} + +/* + * This is only an example! + */ + +int main () +{ + printf("%ld\n", f(15)); + return 0; +} +commit refs/tags/simple +mark :12 +author Thomas Rast 1362044890 +0100 +committer Thomas Rast 1362044890 +0100 +data 36 +change to an incomplete line at end +from :10 +M 100644 :11 a.c + +blob +mark :13 +data 238 +#include +#include + +long f(long x) +{ + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; +} + +/* + * This is only an example! + */ + +int main () +{ + printf("%ld\n", f(15)); + return 0; +} + +/* incomplete lines are bad! */ + +commit refs/tags/simple +mark :14 +author Thomas Rast 1362044923 +0100 +committer Thomas Rast 1362044923 +0100 +data 29 +change back to complete line +from :12 +M 100644 :13 a.c + +commit refs/tags/move-support +mark :15 +author Thomas Rast 1362044968 +0100 +committer Thomas Rast 1362044968 +0100 +data 10 +move file +from :14 +D a.c +M 100644 :13 b.c + +blob +mark :16 +data 237 +#include +#include + +long f(long x) +{ + int s = 0; + while (x) { + x /= 2; + s++; + } + return s; +} + +/* + * This is only an example! + */ + +int main () +{ + printf("%ld\n", f(15)); + return 0; +} + +/* incomplete lines are bad! */ + +commit refs/tags/move-support +mark :17 +author Thomas Rast 1362044990 +0100 +committer Thomas Rast 1362044990 +0100 +data 22 +another simple change +from :15 +M 100644 :16 b.c + +blob +mark :18 +data 254 +#include +#include + +long f(long x); + +/* + * This is only an example! + */ + +int main () +{ + printf("%ld\n", f(15)); + return 0; +} + +/* incomplete lines are bad! */ + +long f(long x) +{ + int s = 0; + while (x) { + x /= 2; + s++; + } + return s; +} + +commit refs/heads/master +mark :19 +author Thomas Rast 1362045024 +0100 +committer Thomas Rast 1362045024 +0100 +data 21 +move within the file +from :17 +M 100644 :18 b.c + +reset refs/heads/master +from :19 + From 13b8f68c1f0b6d4ff5a7bed5a834e7e5e34a9fd0 Mon Sep 17 00:00:00 2001 From: Thomas Rast Date: Thu, 28 Mar 2013 17:47:33 +0100 Subject: [PATCH 04/13] log -L: :pattern:file syntax to find by funcname This new syntax finds a funcname matching /pattern/, and then takes from there up to (but not including) the next funcname. So you can say git log -L:main:main.c and it will dig up the main() function and show its line-log, provided there are no other funcnames matching 'main'. Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- Documentation/blame-options.txt | 2 +- Documentation/git-blame.txt | 6 +- Documentation/git-log.txt | 11 ++- Documentation/line-range-format.txt | 7 ++ builtin/blame.c | 2 +- line-log.c | 5 +- line-range.c | 138 +++++++++++++++++++++++++++- line-range.h | 3 +- t/t4211-line-log.sh | 4 + t/t4211/expect.simple-f-to-main | 100 ++++++++++++++++++++ t/t4211/expect.simple-main-to-end | 70 ++++++++++++++ 11 files changed, 333 insertions(+), 15 deletions(-) create mode 100644 t/t4211/expect.simple-f-to-main create mode 100644 t/t4211/expect.simple-main-to-end diff --git a/Documentation/blame-options.txt b/Documentation/blame-options.txt index 6998d9f5bf..e9f984ba01 100644 --- a/Documentation/blame-options.txt +++ b/Documentation/blame-options.txt @@ -9,7 +9,7 @@ --show-stats:: Include additional statistics at the end of blame output. --L ,:: +-L ,, -L ::: Annotate only the given line range. and can take one of these forms: diff --git a/Documentation/git-blame.txt b/Documentation/git-blame.txt index 9a05c2b3d2..6cea7f1ce1 100644 --- a/Documentation/git-blame.txt +++ b/Documentation/git-blame.txt @@ -8,9 +8,9 @@ git-blame - Show what revision and author last modified each line of a file SYNOPSIS -------- [verse] -'git blame' [-c] [-b] [-l] [--root] [-t] [-f] [-n] [-s] [-e] [-p] [-w] [--incremental] [-L n,m] - [-S ] [-M] [-C] [-C] [-C] [--since=] [--abbrev=] - [ | --contents | --reverse ] [--] +'git blame' [-c] [-b] [-l] [--root] [-t] [-f] [-n] [-s] [-e] [-p] [-w] [--incremental] + [-L n,m | -L :fn] [-S ] [-M] [-C] [-C] [-C] [--since=] + [--abbrev=] [ | --contents | --reverse ] [--] DESCRIPTION ----------- diff --git a/Documentation/git-log.txt b/Documentation/git-log.txt index 8727c60ab3..4850226aaf 100644 --- a/Documentation/git-log.txt +++ b/Documentation/git-log.txt @@ -69,12 +69,13 @@ produced by --stat etc. Note that only message is considered, if also a diff is shown its size is not included. --L ,::: +-L ,:, -L :::: + Trace the evolution of the line range given by "," - within the . You may not give any pathspec limiters. - This is currently limited to a walk starting from a single - revision, i.e., you may only give zero or one positive - revision arguments. + (or the funcname regex ) within the . You may + not give any pathspec limiters. This is currently limited to + a walk starting from a single revision, i.e., you may only + give zero or one positive revision arguments. and can take one of these forms: diff --git a/Documentation/line-range-format.txt b/Documentation/line-range-format.txt index 265bc23290..3e7ce72daa 100644 --- a/Documentation/line-range-format.txt +++ b/Documentation/line-range-format.txt @@ -16,3 +16,10 @@ starting at the line given by . This is only valid for and will specify a number of lines before or after the line given by . + + +- :regex ++ +If the option's argument is of the form :regex, it denotes the range +from the first funcname line that matches , up to the next +funcname line. ++ diff --git a/builtin/blame.c b/builtin/blame.c index 20eb439cb8..1c09d552fa 100644 --- a/builtin/blame.c +++ b/builtin/blame.c @@ -1940,7 +1940,7 @@ static void prepare_blame_range(struct scoreboard *sb, long lno, long *bottom, long *top) { - if (parse_range_arg(bottomtop, nth_line_cb, sb, lno, bottom, top)) + if (parse_range_arg(bottomtop, nth_line_cb, sb, lno, bottom, top, sb->path)) usage(blame_usage); } diff --git a/line-log.c b/line-log.c index 624423142e..68972e24c7 100644 --- a/line-log.c +++ b/line-log.c @@ -12,6 +12,7 @@ #include "strbuf.h" #include "log-tree.h" #include "graph.h" +#include "userdiff.h" #include "line-log.h" static void range_set_grow(struct range_set *rs, size_t extra) @@ -438,7 +439,6 @@ static void range_set_map_across_diff(struct range_set *out, *touched_out = touched; } - static struct commit *check_single_commit(struct rev_info *revs) { struct object *commit = NULL; @@ -559,7 +559,8 @@ parse_lines(struct commit *commit, const char *prefix, struct string_list *args) cb_data.line_ends = ends; if (parse_range_arg(range_part, nth_line, &cb_data, - lines, &begin, &end)) + lines, &begin, &end, + spec->path)) die("malformed -L argument '%s'", range_part); if (begin < 1) begin = 1; diff --git a/line-range.c b/line-range.c index 7a7ca3c2bd..8faf943745 100644 --- a/line-range.c +++ b/line-range.c @@ -1,5 +1,8 @@ #include "git-compat-util.h" #include "line-range.h" +#include "xdiff-interface.h" +#include "strbuf.h" +#include "userdiff.h" /* * Parse one item in the -L option @@ -84,9 +87,137 @@ static const char *parse_loc(const char *spec, nth_line_fn_t nth_line, } } -int parse_range_arg(const char *arg, nth_line_fn_t nth_line_cb, - void *cb_data, long lines, long *begin, long *end) +static int match_funcname(xdemitconf_t *xecfg, const char *bol, const char *eol) { + if (xecfg) { + char buf[1]; + return xecfg->find_func(bol, eol - bol, buf, 1, + xecfg->find_func_priv) >= 0; + } + + if (bol == eol) + return 0; + if (isalpha(*bol) || *bol == '_' || *bol == '$') + return 1; + return 0; +} + +static const char *find_funcname_matching_regexp(xdemitconf_t *xecfg, const char *start, + regex_t *regexp) +{ + int reg_error; + regmatch_t match[1]; + while (1) { + const char *bol, *eol; + reg_error = regexec(regexp, start, 1, match, 0); + if (reg_error == REG_NOMATCH) + return NULL; + else if (reg_error) { + char errbuf[1024]; + regerror(reg_error, regexp, errbuf, 1024); + die("-L parameter: regexec() failed: %s", errbuf); + } + /* determine extent of line matched */ + bol = start+match[0].rm_so; + eol = start+match[0].rm_eo; + while (bol > start && *bol != '\n') + bol--; + if (*bol == '\n') + bol++; + while (*eol && *eol != '\n') + eol++; + if (*eol == '\n') + eol++; + /* is it a funcname line? */ + if (match_funcname(xecfg, (char*) bol, (char*) eol)) + return bol; + start = eol; + } +} + +static const char *parse_range_funcname(const char *arg, nth_line_fn_t nth_line_cb, + void *cb_data, long lines, long *begin, long *end, + const char *path) +{ + char *pattern; + const char *term; + struct userdiff_driver *drv; + xdemitconf_t *xecfg = NULL; + const char *start; + const char *p; + int reg_error; + regex_t regexp; + + assert(*arg == ':'); + term = arg+1; + while (*term && *term != ':') { + if (*term == '\\' && *(term+1)) + term++; + term++; + } + if (term == arg+1) + return NULL; + if (!begin) /* skip_range_arg case */ + return term; + + pattern = xstrndup(arg+1, term-(arg+1)); + + start = nth_line_cb(cb_data, 0); + + drv = userdiff_find_by_path(path); + if (drv && drv->funcname.pattern) { + const struct userdiff_funcname *pe = &drv->funcname; + xecfg = xcalloc(1, sizeof(*xecfg)); + xdiff_set_find_func(xecfg, pe->pattern, pe->cflags); + } + + reg_error = regcomp(®exp, pattern, REG_NEWLINE); + if (reg_error) { + char errbuf[1024]; + regerror(reg_error, ®exp, errbuf, 1024); + die("-L parameter '%s': %s", pattern, errbuf); + } + + p = find_funcname_matching_regexp(xecfg, (char*) start, ®exp); + if (!p) + die("-L parameter '%s': no match", pattern); + *begin = 0; + while (p > nth_line_cb(cb_data, *begin)) + (*begin)++; + + if (*begin >= lines) + die("-L parameter '%s' matches at EOF", pattern); + + *end = *begin+1; + while (*end < lines) { + const char *bol = nth_line_cb(cb_data, *end); + const char *eol = nth_line_cb(cb_data, *end+1); + if (match_funcname(xecfg, bol, eol)) + break; + (*end)++; + } + + regfree(®exp); + free(xecfg); + free(pattern); + + /* compensate for 1-based numbering */ + (*begin)++; + + return term; +} + +int parse_range_arg(const char *arg, nth_line_fn_t nth_line_cb, + void *cb_data, long lines, long *begin, long *end, + const char *path) +{ + if (*arg == ':') { + arg = parse_range_funcname(arg, nth_line_cb, cb_data, lines, begin, end, path); + if (!arg || *arg) + return -1; + return 0; + } + arg = parse_loc(arg, nth_line_cb, cb_data, lines, 1, begin); if (*arg == ',') @@ -100,6 +231,9 @@ int parse_range_arg(const char *arg, nth_line_fn_t nth_line_cb, const char *skip_range_arg(const char *arg) { + if (*arg == ':') + return parse_range_funcname(arg, NULL, NULL, 0, NULL, NULL, NULL); + arg = parse_loc(arg, NULL, NULL, 0, -1, NULL); if (*arg == ',') diff --git a/line-range.h b/line-range.h index 88aaf08b7f..ae3d0123b4 100644 --- a/line-range.h +++ b/line-range.h @@ -19,7 +19,8 @@ typedef const char *(*nth_line_fn_t)(void *data, long lno); extern int parse_range_arg(const char *arg, nth_line_fn_t nth_line_cb, void *cb_data, long lines, - long *begin, long *end); + long *begin, long *end, + const char *path); /* * Scan past a range argument that could be parsed by diff --git a/t/t4211-line-log.sh b/t/t4211-line-log.sh index 9f36f17384..426a82868e 100755 --- a/t/t4211-line-log.sh +++ b/t/t4211-line-log.sh @@ -25,8 +25,10 @@ test_bad_opts () { canned_test "-L 4,12:a.c simple" simple-f canned_test "-L 4,+9:a.c simple" simple-f canned_test "-L '/long f/,/^}/:a.c' simple" simple-f +canned_test "-L :f:a.c simple" simple-f-to-main canned_test "-L '/main/,/^}/:a.c' simple" simple-main +canned_test "-L :main:a.c simple" simple-main-to-end canned_test "-L 1,+4:a.c simple" beginning-of-file @@ -45,5 +47,7 @@ test_bad_opts "-L 1:simple" "There is no path" test_bad_opts "-L '/foo:b.c'" "argument.*not of the form" test_bad_opts "-L 1000:b.c" "has only.*lines" test_bad_opts "-L 1,1000:b.c" "has only.*lines" +test_bad_opts "-L :b.c" "argument.*not of the form" +test_bad_opts "-L :foo:b.c" "no match" test_done diff --git a/t/t4211/expect.simple-f-to-main b/t/t4211/expect.simple-f-to-main new file mode 100644 index 0000000000..a475768710 --- /dev/null +++ b/t/t4211/expect.simple-f-to-main @@ -0,0 +1,100 @@ +commit 39b6eb2d5b706d3322184a169f666f25ed3fbd00 +Author: Thomas Rast +Date: Thu Feb 28 10:45:41 2013 +0100 + + touch comment + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,14 +3,14 @@ + long f(long x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; + } + + /* +- * A comment. ++ * This is only an example! + */ + + +commit a6eb82647d5d67f893da442f8f9375fd89a3b1e2 +Author: Thomas Rast +Date: Thu Feb 28 10:45:16 2013 +0100 + + touch both functions + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,14 +3,14 @@ +-int f(int x) ++long f(long x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; + } + + /* + * A comment. + */ + + +commit f04fb20f2c77850996cba739709acc6faecc58f7 +Author: Thomas Rast +Date: Thu Feb 28 10:44:55 2013 +0100 + + change f() + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,13 +3,14 @@ + int f(int x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } ++ return s; + } + + /* + * A comment. + */ + + +commit de4c48ae814792c02a49c4c3c0c757ae69c55f6a +Author: Thomas Rast +Date: Thu Feb 28 10:44:48 2013 +0100 + + initial + +diff --git a/a.c b/a.c +--- /dev/null ++++ b/a.c +@@ -0,0 +3,13 @@ ++int f(int x) ++{ ++ int s = 0; ++ while (x) { ++ x >>= 1; ++ s++; ++ } ++} ++ ++/* ++ * A comment. ++ */ ++ diff --git a/t/t4211/expect.simple-main-to-end b/t/t4211/expect.simple-main-to-end new file mode 100644 index 0000000000..8480bd9cc4 --- /dev/null +++ b/t/t4211/expect.simple-main-to-end @@ -0,0 +1,70 @@ +commit 4659538844daa2849b1a9e7d6fadb96fcd26fc83 +Author: Thomas Rast +Date: Thu Feb 28 10:48:43 2013 +0100 + + change back to complete line + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -18,5 +18,7 @@ + int main () + { + printf("%ld\n", f(15)); + return 0; +-} +\ No newline at end of file ++} ++ ++/* incomplete lines are bad! */ + +commit 100b61a6f2f720f812620a9d10afb3a960ccb73c +Author: Thomas Rast +Date: Thu Feb 28 10:48:10 2013 +0100 + + change to an incomplete line at end + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -18,5 +18,5 @@ + int main () + { + printf("%ld\n", f(15)); + return 0; +-} ++} +\ No newline at end of file + +commit a6eb82647d5d67f893da442f8f9375fd89a3b1e2 +Author: Thomas Rast +Date: Thu Feb 28 10:45:16 2013 +0100 + + touch both functions + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -17,5 +17,5 @@ + int main () + { +- printf("%d\n", f(15)); ++ printf("%ld\n", f(15)); + return 0; + } + +commit de4c48ae814792c02a49c4c3c0c757ae69c55f6a +Author: Thomas Rast +Date: Thu Feb 28 10:44:48 2013 +0100 + + initial + +diff --git a/a.c b/a.c +--- /dev/null ++++ b/a.c +@@ -0,0 +16,5 @@ ++int main () ++{ ++ printf("%d\n", f(15)); ++ return 0; ++} From 39410bf0bf81cb3f76fb9bfa8308cd672bc1442c Mon Sep 17 00:00:00 2001 From: Thomas Rast Date: Thu, 28 Mar 2013 17:47:34 +0100 Subject: [PATCH 05/13] Speed up log -L... -M So far log -L only used the implicit diff filtering by pathspec. If the user specifies -M, we cannot do that, and so we simply handed the whole diff queue (which is approximately 'git show --raw') to diffcore_std(). Unfortunately this is very slow. We can optimize a lot if we throw out files that we know cannot possibly be interesting, in the same spirit that the pathspec filtering reduces the number of files. However, in this case, we have to be more careful. Because we want to look out for renames, we need to keep all filepairs where something was deleted. This is a bit hacky and should really be replaced by equivalent support in --follow, and just using that. However, in the meantime it speeds up 'log -M -L' by an order of magnitude. Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- line-log.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 52 insertions(+), 4 deletions(-) diff --git a/line-log.c b/line-log.c index 68972e24c7..30edef4bec 100644 --- a/line-log.c +++ b/line-log.c @@ -750,7 +750,50 @@ static void move_diff_queue(struct diff_queue_struct *dst, DIFF_QUEUE_CLEAR(src); } -static void queue_diffs(struct diff_options *opt, +static void filter_diffs_for_paths(struct line_log_data *range, int keep_deletions) +{ + int i; + struct diff_queue_struct outq; + DIFF_QUEUE_CLEAR(&outq); + + for (i = 0; i < diff_queued_diff.nr; i++) { + struct diff_filepair *p = diff_queued_diff.queue[i]; + struct line_log_data *rg = NULL; + + if (!DIFF_FILE_VALID(p->two)) { + if (keep_deletions) + diff_q(&outq, p); + else + diff_free_filepair(p); + continue; + } + for (rg = range; rg; rg = rg->next) { + if (!strcmp(rg->spec->path, p->two->path)) + break; + } + if (rg) + diff_q(&outq, p); + else + diff_free_filepair(p); + } + free(diff_queued_diff.queue); + diff_queued_diff = outq; +} + +static inline int diff_might_be_rename(void) +{ + int i; + for (i = 0; i < diff_queued_diff.nr; i++) + if (!DIFF_FILE_VALID(diff_queued_diff.queue[i]->one)) { + /* fprintf(stderr, "diff_might_be_rename found creation of: %s\n", */ + /* diff_queued_diff.queue[i]->two->path); */ + return 1; + } + return 0; +} + +static void queue_diffs(struct line_log_data *range, + struct diff_options *opt, struct diff_queue_struct *queue, struct commit *commit, struct commit *parent) { @@ -766,7 +809,12 @@ static void queue_diffs(struct diff_options *opt, DIFF_QUEUE_CLEAR(&diff_queued_diff); diff_tree(&desc1, &desc2, "", opt); - diffcore_std(opt); + if (opt->detect_rename) { + filter_diffs_for_paths(range, 1); + if (diff_might_be_rename()) + diffcore_std(opt); + filter_diffs_for_paths(range, 0); + } move_diff_queue(queue, &diff_queued_diff); if (tree1) @@ -1050,7 +1098,7 @@ static int process_ranges_ordinary_commit(struct rev_info *rev, struct commit *c if (commit->parents) parent = commit->parents->item; - queue_diffs(&rev->diffopt, &queue, commit, parent); + queue_diffs(range, &rev->diffopt, &queue, commit, parent); changed = process_all_files(&parent_range, rev, &queue, range); if (parent) add_line_range(rev, parent, parent_range); @@ -1075,7 +1123,7 @@ static int process_ranges_merge_commit(struct rev_info *rev, struct commit *comm for (i = 0; i < nparents; i++) { parents[i] = p->item; p = p->next; - queue_diffs(&rev->diffopt, &diffqueues[i], commit, parents[i]); + queue_diffs(range, &rev->diffopt, &diffqueues[i], commit, parents[i]); } for (i = 0; i < nparents; i++) { From 4596f190d384872305e502ebece2e38358ba463e Mon Sep 17 00:00:00 2001 From: Thomas Rast Date: Fri, 5 Apr 2013 16:34:47 +0200 Subject: [PATCH 06/13] log -L: check range set invariants when we look it up lookup_line_range() is a good place to check that the range sets satisfy the invariants: they have been computed and set in earlier iterations, and we now start working with them. Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- line-log.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/line-log.c b/line-log.c index 30edef4bec..5a12ceb012 100644 --- a/line-log.c +++ b/line-log.c @@ -79,6 +79,25 @@ static int range_cmp(const void *_r, const void *_s) return 1; } +/* + * Check that the ranges are non-empty, sorted and non-overlapping + */ +static void range_set_check_invariants(struct range_set *rs) +{ + int i; + + if (!rs) + return; + + if (rs->nr) + assert(rs->ranges[0].start < rs->ranges[0].end); + + for (i = 1; i < rs->nr; i++) { + assert(rs->ranges[i-1].end < rs->ranges[i].start); + assert(rs->ranges[i].start < rs->ranges[i].end); + } +} + /* * Helper: In-place pass of sorting and merging the ranges in the * range set, to re-establish the invariants after another operation @@ -103,6 +122,8 @@ static void sort_and_merge_range_set(struct range_set *rs) } assert(o <= rs->nr); rs->nr = o; + + range_set_check_invariants(rs); } /* @@ -687,8 +708,13 @@ static struct line_log_data *lookup_line_range(struct rev_info *revs, struct commit *commit) { struct line_log_data *ret = NULL; + struct line_log_data *d; ret = lookup_decoration(&revs->line_log_data, &commit->object); + + for (d = ret; d; d = d->next) + range_set_check_invariants(&d->ranges); + return ret; } From 209618860c2627a4e134a15472587c574b328b40 Mon Sep 17 00:00:00 2001 From: Thomas Rast Date: Fri, 5 Apr 2013 16:34:48 +0200 Subject: [PATCH 07/13] log -L: fix overlapping input ranges The existing code was too defensive, and would trigger the assert in range_set_append() if the user gave overlapping ranges. The intent was always to define overlapping ranges as just the union of all of them, as evidenced by the call to sort_and_merge_range_set(). (Which was already used, unlike what the comment said.) Fix by splitting out the meat of range_set_append() to a new _unsafe() function that lacks the paranoia. sort_and_merge_range_set will fix up the ranges, so we don't need the checks there. Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- line-log.c | 17 +-- t/t4211-line-log.sh | 6 + t/t4211/expect.multiple | 104 ++++++++++++++++ t/t4211/expect.multiple-overlapping | 187 ++++++++++++++++++++++++++++ t/t4211/expect.multiple-superset | 59 +++++++++ 5 files changed, 366 insertions(+), 7 deletions(-) create mode 100644 t/t4211/expect.multiple create mode 100644 t/t4211/expect.multiple-overlapping create mode 100644 t/t4211/expect.multiple-superset diff --git a/line-log.c b/line-log.c index 5a12ceb012..85c7c249f4 100644 --- a/line-log.c +++ b/line-log.c @@ -56,16 +56,21 @@ static void range_set_move(struct range_set *dst, struct range_set *src) } /* tack on a _new_ range _at the end_ */ -static void range_set_append(struct range_set *rs, long a, long b) +static void range_set_append_unsafe(struct range_set *rs, long a, long b) { assert(a <= b); - assert(rs->nr == 0 || rs->ranges[rs->nr-1].end <= a); range_set_grow(rs, 1); rs->ranges[rs->nr].start = a; rs->ranges[rs->nr].end = b; rs->nr++; } +static void range_set_append(struct range_set *rs, long a, long b) +{ + assert(rs->nr == 0 || rs->ranges[rs->nr-1].end <= a); + range_set_append_unsafe(rs, a, b); +} + static int range_cmp(const void *_r, const void *_s) { const struct range *r = _r; @@ -99,10 +104,8 @@ static void range_set_check_invariants(struct range_set *rs) } /* - * Helper: In-place pass of sorting and merging the ranges in the - * range set, to re-establish the invariants after another operation - * - * NEEDSWORK currently not needed + * In-place pass of sorting and merging the ranges in the range set, + * to establish the invariants when we get the ranges from the user */ static void sort_and_merge_range_set(struct range_set *rs) { @@ -280,7 +283,7 @@ static void line_log_data_insert(struct line_log_data **list, struct line_log_data *p = search_line_log_data(*list, spec->path, &ip); if (p) { - range_set_append(&p->ranges, begin, end); + range_set_append_unsafe(&p->ranges, begin, end); sort_and_merge_range_set(&p->ranges); free_filespec(spec); return; diff --git a/t/t4211-line-log.sh b/t/t4211-line-log.sh index 426a82868e..2341351e1b 100755 --- a/t/t4211-line-log.sh +++ b/t/t4211-line-log.sh @@ -39,6 +39,12 @@ canned_test "-L 24,+1:a.c simple" vanishes-early canned_test "-L '/long f/,/^}/:b.c' move-support" move-support-f +canned_test "-L 4,12:a.c -L :main:a.c simple" multiple +canned_test "-L 4,18:a.c -L :main:a.c simple" multiple-overlapping +canned_test "-L :main:a.c -L 4,18:a.c simple" multiple-overlapping +canned_test "-L 4:a.c -L 8,12:a.c simple" multiple-superset +canned_test "-L 8,12:a.c -L 4:a.c simple" multiple-superset + test_bad_opts "-L" "switch.*requires a value" test_bad_opts "-L b.c" "argument.*not of the form" test_bad_opts "-L 1:" "argument.*not of the form" diff --git a/t/t4211/expect.multiple b/t/t4211/expect.multiple new file mode 100644 index 0000000000..76ad5b598c --- /dev/null +++ b/t/t4211/expect.multiple @@ -0,0 +1,104 @@ +commit 4659538844daa2849b1a9e7d6fadb96fcd26fc83 +Author: Thomas Rast +Date: Thu Feb 28 10:48:43 2013 +0100 + + change back to complete line + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -18,5 +18,7 @@ + int main () + { + printf("%ld\n", f(15)); + return 0; +-} +\ No newline at end of file ++} ++ ++/* incomplete lines are bad! */ + +commit 100b61a6f2f720f812620a9d10afb3a960ccb73c +Author: Thomas Rast +Date: Thu Feb 28 10:48:10 2013 +0100 + + change to an incomplete line at end + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -18,5 +18,5 @@ + int main () + { + printf("%ld\n", f(15)); + return 0; +-} ++} +\ No newline at end of file + +commit a6eb82647d5d67f893da442f8f9375fd89a3b1e2 +Author: Thomas Rast +Date: Thu Feb 28 10:45:16 2013 +0100 + + touch both functions + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,9 +3,9 @@ +-int f(int x) ++long f(long x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; + } +@@ -17,5 +17,5 @@ + int main () + { +- printf("%d\n", f(15)); ++ printf("%ld\n", f(15)); + return 0; + } + +commit f04fb20f2c77850996cba739709acc6faecc58f7 +Author: Thomas Rast +Date: Thu Feb 28 10:44:55 2013 +0100 + + change f() + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,8 +3,9 @@ + int f(int x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } ++ return s; + } + +commit de4c48ae814792c02a49c4c3c0c757ae69c55f6a +Author: Thomas Rast +Date: Thu Feb 28 10:44:48 2013 +0100 + + initial + +diff --git a/a.c b/a.c +--- /dev/null ++++ b/a.c +@@ -0,0 +3,8 @@ ++int f(int x) ++{ ++ int s = 0; ++ while (x) { ++ x >>= 1; ++ s++; ++ } ++} diff --git a/t/t4211/expect.multiple-overlapping b/t/t4211/expect.multiple-overlapping new file mode 100644 index 0000000000..d930b6eec4 --- /dev/null +++ b/t/t4211/expect.multiple-overlapping @@ -0,0 +1,187 @@ +commit 4659538844daa2849b1a9e7d6fadb96fcd26fc83 +Author: Thomas Rast +Date: Thu Feb 28 10:48:43 2013 +0100 + + change back to complete line + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -4,19 +4,21 @@ + long f(long x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; + } + + /* + * This is only an example! + */ + + int main () + { + printf("%ld\n", f(15)); + return 0; +-} +\ No newline at end of file ++} ++ ++/* incomplete lines are bad! */ + +commit 100b61a6f2f720f812620a9d10afb3a960ccb73c +Author: Thomas Rast +Date: Thu Feb 28 10:48:10 2013 +0100 + + change to an incomplete line at end + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -4,19 +4,19 @@ + long f(long x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; + } + + /* + * This is only an example! + */ + + int main () + { + printf("%ld\n", f(15)); + return 0; +-} ++} +\ No newline at end of file + +commit 39b6eb2d5b706d3322184a169f666f25ed3fbd00 +Author: Thomas Rast +Date: Thu Feb 28 10:45:41 2013 +0100 + + touch comment + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,19 +3,19 @@ + long f(long x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; + } + + /* +- * A comment. ++ * This is only an example! + */ + + int main () + { + printf("%ld\n", f(15)); + return 0; + } + +commit a6eb82647d5d67f893da442f8f9375fd89a3b1e2 +Author: Thomas Rast +Date: Thu Feb 28 10:45:16 2013 +0100 + + touch both functions + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,19 +3,19 @@ +-int f(int x) ++long f(long x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; + } + + /* + * A comment. + */ + + int main () + { +- printf("%d\n", f(15)); ++ printf("%ld\n", f(15)); + return 0; + } + +commit f04fb20f2c77850996cba739709acc6faecc58f7 +Author: Thomas Rast +Date: Thu Feb 28 10:44:55 2013 +0100 + + change f() + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,18 +3,19 @@ + int f(int x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } ++ return s; + } + + /* + * A comment. + */ + + int main () + { + printf("%d\n", f(15)); + return 0; + } + +commit de4c48ae814792c02a49c4c3c0c757ae69c55f6a +Author: Thomas Rast +Date: Thu Feb 28 10:44:48 2013 +0100 + + initial + +diff --git a/a.c b/a.c +--- /dev/null ++++ b/a.c +@@ -0,0 +3,18 @@ ++int f(int x) ++{ ++ int s = 0; ++ while (x) { ++ x >>= 1; ++ s++; ++ } ++} ++ ++/* ++ * A comment. ++ */ ++ ++int main () ++{ ++ printf("%d\n", f(15)); ++ return 0; ++} diff --git a/t/t4211/expect.multiple-superset b/t/t4211/expect.multiple-superset new file mode 100644 index 0000000000..a1f5bc49c8 --- /dev/null +++ b/t/t4211/expect.multiple-superset @@ -0,0 +1,59 @@ +commit a6eb82647d5d67f893da442f8f9375fd89a3b1e2 +Author: Thomas Rast +Date: Thu Feb 28 10:45:16 2013 +0100 + + touch both functions + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,9 +3,9 @@ +-int f(int x) ++long f(long x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; + } + +commit f04fb20f2c77850996cba739709acc6faecc58f7 +Author: Thomas Rast +Date: Thu Feb 28 10:44:55 2013 +0100 + + change f() + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,8 +3,9 @@ + int f(int x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } ++ return s; + } + +commit de4c48ae814792c02a49c4c3c0c757ae69c55f6a +Author: Thomas Rast +Date: Thu Feb 28 10:44:48 2013 +0100 + + initial + +diff --git a/a.c b/a.c +--- /dev/null ++++ b/a.c +@@ -0,0 +3,8 @@ ++int f(int x) ++{ ++ int s = 0; ++ while (x) { ++ x >>= 1; ++ s++; ++ } ++} From 035ff3987bcbe93a823f47befbe019319c1484b0 Mon Sep 17 00:00:00 2001 From: Thomas Rast Date: Fri, 12 Apr 2013 18:05:09 +0200 Subject: [PATCH 08/13] t4211: pass -M to 'git log -M -L...' test Embarrassingly, the -M test did not actually invoke -M, and thus not really test the feature. Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- t/t4211-line-log.sh | 2 +- t/t4211/expect.move-support-f | 56 ++++++++++++++++++++++++++++++----- 2 files changed, 49 insertions(+), 9 deletions(-) diff --git a/t/t4211-line-log.sh b/t/t4211-line-log.sh index 2341351e1b..2a67e31bd7 100755 --- a/t/t4211-line-log.sh +++ b/t/t4211-line-log.sh @@ -37,7 +37,7 @@ canned_test "-L 20:a.c simple" end-of-file canned_test "-L '/long f/',/^}/:a.c -L /main/,/^}/:a.c simple" two-ranges canned_test "-L 24,+1:a.c simple" vanishes-early -canned_test "-L '/long f/,/^}/:b.c' move-support" move-support-f +canned_test "-M -L '/long f/,/^}/:b.c' move-support" move-support-f canned_test "-L 4,12:a.c -L :main:a.c simple" multiple canned_test "-L 4,18:a.c -L :main:a.c simple" multiple-overlapping diff --git a/t/t4211/expect.move-support-f b/t/t4211/expect.move-support-f index 78a8cf1afd..c905e01bc2 100644 --- a/t/t4211/expect.move-support-f +++ b/t/t4211/expect.move-support-f @@ -19,22 +19,62 @@ diff --git a/b.c b/b.c return s; } -commit e6da343666244ea9e67cbe3f3bd26da860f9fe0e +commit a6eb82647d5d67f893da442f8f9375fd89a3b1e2 Author: Thomas Rast -Date: Thu Feb 28 10:49:28 2013 +0100 +Date: Thu Feb 28 10:45:16 2013 +0100 - move file + touch both functions -diff --git a/b.c b/b.c ---- /dev/null -+++ b/b.c -@@ -0,0 +4,9 @@ +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,9 +3,9 @@ +-int f(int x) +long f(long x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; + } + +commit f04fb20f2c77850996cba739709acc6faecc58f7 +Author: Thomas Rast +Date: Thu Feb 28 10:44:55 2013 +0100 + + change f() + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,8 +3,9 @@ + int f(int x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } ++ return s; + } + +commit de4c48ae814792c02a49c4c3c0c757ae69c55f6a +Author: Thomas Rast +Date: Thu Feb 28 10:44:48 2013 +0100 + + initial + +diff --git a/a.c b/a.c +--- /dev/null ++++ b/a.c +@@ -0,0 +3,8 @@ ++int f(int x) +{ + int s = 0; + while (x) { + x >>= 1; + s++; + } -+ return s; +} From d51c5274e458e9c2545144b6821978ccda85c117 Mon Sep 17 00:00:00 2001 From: Thomas Rast Date: Fri, 12 Apr 2013 18:05:10 +0200 Subject: [PATCH 09/13] log -L: test merge of parallel modify/rename This tests a toy example of a history like * Merge | \ | * Modify foo | | * | Rename foo->bar | / * Create foo Current log -L fails on this; we'll fix it in the next commit. Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- t/t4211-line-log.sh | 16 ++- t/t4211/expect.parallel-change-f-to-main | 160 +++++++++++++++++++++++ t/t4211/history.export | 80 +++++++++++- 3 files changed, 250 insertions(+), 6 deletions(-) create mode 100644 t/t4211/expect.parallel-change-f-to-main diff --git a/t/t4211-line-log.sh b/t/t4211-line-log.sh index 2a67e31bd7..bba0b093d5 100755 --- a/t/t4211-line-log.sh +++ b/t/t4211-line-log.sh @@ -8,13 +8,20 @@ test_expect_success 'setup (import history)' ' git reset --hard ' -canned_test () { - test_expect_success "$1" " - git log $1 >actual && - test_cmp \"\$TEST_DIRECTORY\"/t4211/expect.$2 actual +canned_test_1 () { + test_expect_$1 "$2" " + git log $2 >actual && + test_cmp \"\$TEST_DIRECTORY\"/t4211/expect.$3 actual " } +canned_test () { + canned_test_1 success "$@" +} +canned_test_failure () { + canned_test_1 failure "$@" +} + test_bad_opts () { test_expect_success "invalid args: $1" " test_must_fail git log $1 2>errors && @@ -38,6 +45,7 @@ canned_test "-L '/long f/',/^}/:a.c -L /main/,/^}/:a.c simple" two-ranges canned_test "-L 24,+1:a.c simple" vanishes-early canned_test "-M -L '/long f/,/^}/:b.c' move-support" move-support-f +canned_test_failure "-M -L ':f:b.c' parallel-change" parallel-change-f-to-main canned_test "-L 4,12:a.c -L :main:a.c simple" multiple canned_test "-L 4,18:a.c -L :main:a.c simple" multiple-overlapping diff --git a/t/t4211/expect.parallel-change-f-to-main b/t/t4211/expect.parallel-change-f-to-main new file mode 100644 index 0000000000..052def8074 --- /dev/null +++ b/t/t4211/expect.parallel-change-f-to-main @@ -0,0 +1,160 @@ +commit 0469c60bc4837d52d97b1f081dec5f98dea20fed +Merge: ba227c6 6ce3c4f +Author: Thomas Rast +Date: Fri Apr 12 16:16:24 2013 +0200 + + Merge across the rename + + +commit 6ce3c4ff690136099bb17e1a8766b75764726ea7 +Author: Thomas Rast +Date: Thu Feb 28 10:49:50 2013 +0100 + + another simple change + +diff --git a/b.c b/b.c +--- a/b.c ++++ b/b.c +@@ -4,14 +4,14 @@ + long f(long x) + { + int s = 0; + while (x) { +- x >>= 1; ++ x /= 2; + s++; + } + return s; + } + + /* + * This is only an example! + */ + + +commit ba227c6632349700fbb957dec2b50f5e2358be3f +Author: Thomas Rast +Date: Fri Apr 12 16:15:57 2013 +0200 + + change on another line of history while rename happens + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -4,14 +4,14 @@ + long f(long x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; + } + + /* +- * This is only an example! ++ * This is only a short example! + */ + + +commit 39b6eb2d5b706d3322184a169f666f25ed3fbd00 +Author: Thomas Rast +Date: Thu Feb 28 10:45:41 2013 +0100 + + touch comment + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,14 +3,14 @@ + long f(long x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; + } + + /* +- * A comment. ++ * This is only an example! + */ + + +commit a6eb82647d5d67f893da442f8f9375fd89a3b1e2 +Author: Thomas Rast +Date: Thu Feb 28 10:45:16 2013 +0100 + + touch both functions + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,14 +3,14 @@ +-int f(int x) ++long f(long x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; + } + + /* + * A comment. + */ + + +commit f04fb20f2c77850996cba739709acc6faecc58f7 +Author: Thomas Rast +Date: Thu Feb 28 10:44:55 2013 +0100 + + change f() + +diff --git a/a.c b/a.c +--- a/a.c ++++ b/a.c +@@ -3,13 +3,14 @@ + int f(int x) + { + int s = 0; + while (x) { + x >>= 1; + s++; + } ++ return s; + } + + /* + * A comment. + */ + + +commit de4c48ae814792c02a49c4c3c0c757ae69c55f6a +Author: Thomas Rast +Date: Thu Feb 28 10:44:48 2013 +0100 + + initial + +diff --git a/a.c b/a.c +--- /dev/null ++++ b/a.c +@@ -0,0 +3,13 @@ ++int f(int x) ++{ ++ int s = 0; ++ while (x) { ++ x >>= 1; ++ s++; ++ } ++} ++ ++/* ++ * A comment. ++ */ ++ diff --git a/t/t4211/history.export b/t/t4211/history.export index c159794740..f9f41e211e 100644 --- a/t/t4211/history.export +++ b/t/t4211/history.export @@ -325,6 +325,82 @@ move within the file from :17 M 100644 :18 b.c -reset refs/heads/master -from :19 +blob +mark :20 +data 243 +#include +#include + +long f(long x) +{ + int s = 0; + while (x) { + x >>= 1; + s++; + } + return s; +} + +/* + * This is only a short example! + */ + +int main () +{ + printf("%ld\n", f(15)); + return 0; +} + +/* incomplete lines are bad! */ + +commit refs/heads/parallel-change +mark :21 +author Thomas Rast 1365776157 +0200 +committer Thomas Rast 1365776157 +0200 +data 55 +change on another line of history while rename happens +from :14 +M 100644 :20 a.c + +blob +mark :22 +data 242 +#include +#include + +long f(long x) +{ + int s = 0; + while (x) { + x /= 2; + s++; + } + return s; +} + +/* + * This is only a short example! + */ + +int main () +{ + printf("%ld\n", f(15)); + return 0; +} + +/* incomplete lines are bad! */ + +commit refs/heads/parallel-change +mark :23 +author Thomas Rast 1365776184 +0200 +committer Thomas Rast 1365776191 +0200 +data 24 +Merge across the rename +from :21 +merge :17 +D a.c +M 100644 :22 b.c + +reset refs/heads/parallel-change +from :23 From 31c61918313c7057a48ac939d8699860e8bfff99 Mon Sep 17 00:00:00 2001 From: Thomas Rast Date: Fri, 12 Apr 2013 18:05:11 +0200 Subject: [PATCH 10/13] log -L: store the path instead of a diff_filespec line_log_data has held a diff_filespec* since the very early versions of the code. However, the only place in the code where we actually need the full filespec is parse_range_arg(); in all other cases, we are only interested in the path, so there is hardly a reason to store a filespec. Even worse, it causes a lot of redundant ->spec->path pointer dereferencing. And *even* worse, it caused the following bug. If you merge a rename with a modification to the old filename, like so: * Merge | \ | * Modify foo | | * | Rename foo->bar | / * Create foo we internally -- in process_ranges_merge_commit() -- scan all parents. We are mainly looking for one that doesn't have any modifications, so that we can assign all the blame to it and simplify away the merge. In doing so, we run the normal machinery on all parents in a loop. For each parent, we prepare a "working set" line_log_data by making a copy with line_log_data_copy(), which does *not* make a copy of the spec. Now suppose the rename is the first parent. The diff machinery tells us that the filepair is ('foo', 'bar'). We duly update the path we are interested in: rg->spec->path = xstrdup(pair->one->path); But that 'struct spec' is shared between the output line_log_data and the original input line_log_data. So we just wrecked the state of process_ranges_merge_commit(). When we get around to the second parent, the ranges tell us we are interested in a file 'foo' while the commits touch 'bar'. So most of this patch is just s/->spec->path/->path/ and associated management changes. This implicitly fixes the bug because we removed the shared parts between input and output of line_log_data_copy(); it is now safe to overwrite the path in the copy. There's one only somewhat related change: the comment in process_all_files() explains the reasoning behind using 'range' there. That bit of half-correct code had me sidetracked for a while. Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- line-log.c | 45 ++++++++++++++++++++++++--------------------- line-log.h | 8 ++++++-- t/t4211-line-log.sh | 2 +- 3 files changed, 31 insertions(+), 24 deletions(-) diff --git a/line-log.c b/line-log.c index 85c7c249f4..44d1cd510d 100644 --- a/line-log.c +++ b/line-log.c @@ -265,7 +265,7 @@ search_line_log_data(struct line_log_data *list, const char *path, if (insertion_point) *insertion_point = NULL; while (p) { - int cmp = strcmp(p->spec->path, path); + int cmp = strcmp(p->path, path); if (!cmp) return p; if (insertion_point && cmp < 0) @@ -275,22 +275,26 @@ search_line_log_data(struct line_log_data *list, const char *path, return NULL; } +/* + * Note: takes ownership of 'path', which happens to be what the only + * caller needs. + */ static void line_log_data_insert(struct line_log_data **list, - struct diff_filespec *spec, + char *path, long begin, long end) { struct line_log_data *ip; - struct line_log_data *p = search_line_log_data(*list, spec->path, &ip); + struct line_log_data *p = search_line_log_data(*list, path, &ip); if (p) { range_set_append_unsafe(&p->ranges, begin, end); sort_and_merge_range_set(&p->ranges); - free_filespec(spec); + free(path); return; } p = xcalloc(1, sizeof(struct line_log_data)); - p->spec = spec; + p->path = path; range_set_append(&p->ranges, begin, end); if (ip) { p->next = ip->next; @@ -354,7 +358,7 @@ static void dump_line_log_data(struct line_log_data *r) { char buf[4096]; while (r) { - snprintf(buf, 4096, "file %s\n", r->spec->path); + snprintf(buf, 4096, "file %s\n", r->path); dump_range_set(&r->ranges, buf); r = r->next; } @@ -561,7 +565,7 @@ parse_lines(struct commit *commit, const char *prefix, struct string_list *args) for_each_string_list_item(item, args) { const char *name_part, *range_part; - const char *full_name; + char *full_name; struct diff_filespec *spec; long begin = 0, end = 0; @@ -584,7 +588,7 @@ parse_lines(struct commit *commit, const char *prefix, struct string_list *args) if (parse_range_arg(range_part, nth_line, &cb_data, lines, &begin, &end, - spec->path)) + full_name)) die("malformed -L argument '%s'", range_part); if (begin < 1) begin = 1; @@ -593,8 +597,9 @@ parse_lines(struct commit *commit, const char *prefix, struct string_list *args) begin--; if (lines < end || lines < begin) die("file %s has only %ld lines", name_part, lines); - line_log_data_insert(&ranges, spec, begin, end); + line_log_data_insert(&ranges, full_name, begin, end); + free_filespec(spec); free(ends); ends = NULL; } @@ -610,9 +615,7 @@ static struct line_log_data *line_log_data_copy_one(struct line_log_data *r) line_log_data_init(ret); range_set_copy(&ret->ranges, &r->ranges); - ret->spec = r->spec; - assert(ret->spec); - ret->spec->count++; + ret->path = xstrdup(r->path); return ret; } @@ -652,7 +655,7 @@ static struct line_log_data *line_log_data_merge(struct line_log_data *a, else if (!b) cmp = -1; else - cmp = strcmp(a->spec->path, b->spec->path); + cmp = strcmp(a->path, b->path); if (cmp < 0) { src = a; a = a->next; @@ -667,8 +670,7 @@ static struct line_log_data *line_log_data_merge(struct line_log_data *a, } d = xmalloc(sizeof(struct line_log_data)); line_log_data_init(d); - d->spec = src->spec; - d->spec->count++; + d->path = xstrdup(src->path); *pp = d; pp = &d->next; if (src2) @@ -741,7 +743,7 @@ void line_log_init(struct rev_info *rev, const char *prefix, struct string_list paths = xmalloc((count+1)*sizeof(char *)); r = range; for (i = 0; i < count; i++) { - paths[i] = xstrdup(r->spec->path); + paths[i] = xstrdup(r->path); r = r->next; } paths[count] = NULL; @@ -797,7 +799,7 @@ static void filter_diffs_for_paths(struct line_log_data *range, int keep_deletio continue; } for (rg = range; rg; rg = rg->next) { - if (!strcmp(rg->spec->path, p->two->path)) + if (!strcmp(rg->path, p->two->path)) break; } if (rg) @@ -1021,8 +1023,8 @@ static int process_diff_filepair(struct rev_info *rev, assert(pair->two->path); while (rg) { - assert(rg->spec->path); - if (!strcmp(rg->spec->path, pair->two->path)) + assert(rg->path); + if (!strcmp(rg->path, pair->two->path)) break; rg = rg->next; } @@ -1050,7 +1052,8 @@ static int process_diff_filepair(struct rev_info *rev, collect_diff(&file_parent, &file_target, &diff); /* NEEDSWORK should apply some heuristics to prevent mismatches */ - rg->spec->path = xstrdup(pair->one->path); + free(rg->path); + rg->path = xstrdup(pair->one->path); range_set_init(&tmp, 0); range_set_map_across_diff(&tmp, &rg->ranges, &diff, diff_out); @@ -1096,7 +1099,7 @@ static int process_all_files(struct line_log_data **range_out, struct line_log_data *rg = range; changed++; /* NEEDSWORK tramples over data structures not owned here */ - while (rg && strcmp(rg->spec->path, queue->queue[i]->two->path)) + while (rg && strcmp(rg->path, queue->queue[i]->two->path)) rg = rg->next; assert(rg); rg->pair = diff_filepair_dup(queue->queue[i]); diff --git a/line-log.h b/line-log.h index 9acd12361a..8bea45fd78 100644 --- a/line-log.h +++ b/line-log.h @@ -26,10 +26,14 @@ struct diff_ranges { }; /* Linked list of interesting files and their associated ranges. The - * list must be kept sorted by spec->path */ + * list must be kept sorted by path. + * + * For simplicity, even though this is highly redundant, each + * line_log_data owns its 'path'. + */ struct line_log_data { struct line_log_data *next; - struct diff_filespec *spec; + char *path; char status; struct range_set ranges; int arg_alloc, arg_nr; diff --git a/t/t4211-line-log.sh b/t/t4211-line-log.sh index bba0b093d5..7776f93e3d 100755 --- a/t/t4211-line-log.sh +++ b/t/t4211-line-log.sh @@ -45,7 +45,7 @@ canned_test "-L '/long f/',/^}/:a.c -L /main/,/^}/:a.c simple" two-ranges canned_test "-L 24,+1:a.c simple" vanishes-early canned_test "-M -L '/long f/,/^}/:b.c' move-support" move-support-f -canned_test_failure "-M -L ':f:b.c' parallel-change" parallel-change-f-to-main +canned_test "-M -L ':f:b.c' parallel-change" parallel-change-f-to-main canned_test "-L 4,12:a.c -L :main:a.c simple" multiple canned_test "-L 4,18:a.c -L :main:a.c simple" multiple-overlapping From 1ddac3ff9aa29d1103aa05f59772812289b4cefa Mon Sep 17 00:00:00 2001 From: Thomas Rast Date: Fri, 12 Apr 2013 18:05:12 +0200 Subject: [PATCH 11/13] log -L: improve comments in process_all_files() The funny range assignment in process_all_files() had me sidetracked while investigating what led to the previous commit. Let's improve the comments. Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- line-log.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/line-log.c b/line-log.c index 44d1cd510d..4bbb09be59 100644 --- a/line-log.c +++ b/line-log.c @@ -1095,11 +1095,24 @@ static int process_all_files(struct line_log_data **range_out, for (i = 0; i < queue->nr; i++) { struct diff_ranges *pairdiff = NULL; - if (process_diff_filepair(rev, queue->queue[i], *range_out, &pairdiff)) { + struct diff_filepair *pair = queue->queue[i]; + if (process_diff_filepair(rev, pair, *range_out, &pairdiff)) { + /* + * Store away the diff for later output. We + * tuck it in the ranges we got as _input_, + * since that's the commit that caused the + * diff. + * + * NEEDSWORK not enough when we get around to + * doing something interesting with merges; + * currently each invocation on a merge parent + * trashes the previous one's diff. + * + * NEEDSWORK tramples over data structures not owned here + */ struct line_log_data *rg = range; changed++; - /* NEEDSWORK tramples over data structures not owned here */ - while (rg && strcmp(rg->path, queue->queue[i]->two->path)) + while (rg && strcmp(rg->path, pair->two->path)) rg = rg->next; assert(rg); rg->pair = diff_filepair_dup(queue->queue[i]); From 0f483436e9c2e03bbb80c1dc215d4d7bf8774282 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Sun, 21 Apr 2013 19:40:49 -0700 Subject: [PATCH 12/13] line-log: fix documentation formatting The second paragraph of the added description for the -L option " and can take one of these forms:", and the list of forms that follow the headline, were indented one level too short, due to the missing "+" to signal that the next paragraph continues the previous one. Also "You can specify this option more than once" is about the -L option, not about its various forms of starting and ending points. Move it to the end of the main text. Signed-off-by: Junio C Hamano --- Documentation/git-log.txt | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/Documentation/git-log.txt b/Documentation/git-log.txt index 4850226aaf..0959f9d60c 100644 --- a/Documentation/git-log.txt +++ b/Documentation/git-log.txt @@ -76,12 +76,11 @@ produced by --stat etc. not give any pathspec limiters. This is currently limited to a walk starting from a single revision, i.e., you may only give zero or one positive revision arguments. - + You can specify this option more than once. ++ and can take one of these forms: include::line-range-format.txt[] -You can specify this option more than once. - --full-line-diff:: Always print the interesting range even if the current commit From 499926670665570d785bc7baca4d7cd4420823dc Mon Sep 17 00:00:00 2001 From: Thomas Rast Date: Mon, 22 Apr 2013 11:36:22 +0200 Subject: [PATCH 13/13] git-log(1): remove --full-line-diff description This option is a remnant of an earlier log -L version, and not currently implemented. Remove it until (if at all) it is implemented again. Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- Documentation/git-log.txt | 4 ---- 1 file changed, 4 deletions(-) diff --git a/Documentation/git-log.txt b/Documentation/git-log.txt index 0959f9d60c..65707ce13c 100644 --- a/Documentation/git-log.txt +++ b/Documentation/git-log.txt @@ -82,10 +82,6 @@ produced by --stat etc. include::line-range-format.txt[] ---full-line-diff:: - Always print the interesting range even if the current commit - does not change any line of the range. - [\--] ...:: Show only commits that are enough to explain how the files that match the specified paths came to be. See "History