git/line-range.c
Thomas Rast 12da1d1f6f 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 <jnareb@gmail.com>
  Jens Lehmann <Jens.Lehmann@web.de>
  Jonathan Nieder <jrnieder@gmail.com>
  Junio C Hamano <gitster@pobox.com>
  Ramsay Jones <ramsay@ramsay1.demon.co.uk>
  Will Palmer <wmpalmer@gmail.com>

Apologies to everyone I forgot.

Signed-off-by: Bo Yang <struggleyb.nku@gmail.com>
Signed-off-by: Thomas Rast <trast@student.ethz.ch>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-28 10:29:22 -07:00

110 lines
2.3 KiB
C

#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 <something>,+20" to mean starting at <something>
* for 20 lines, or "-L <something>,-5" for 5 lines ending at
* <something>.
*/
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)
*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) {
if (ret)
*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;
/* 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 */
line = nth_line(data, begin);
if (!(reg_error = regcomp(&regexp, spec + 1, REG_NEWLINE)) &&
!(reg_error = regexec(&regexp, 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(&regexp);
*term++ = '/';
return term;
}
else {
char errbuf[1024];
regerror(reg_error, &regexp, 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;
}
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;
}