|
|
|
#ifndef LINE_RANGE_H
|
|
|
|
#define LINE_RANGE_H
|
|
|
|
|
|
|
|
struct index_state;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*
|
|
|
|
* 'anchor' is the 1-based line at which relative range specifications
|
|
|
|
* should be anchored. Absolute ranges are unaffected by this value.
|
|
|
|
*
|
|
|
|
* 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);
|
|
|
|
|
|
|
|
int parse_range_arg(const char *arg,
|
|
|
|
nth_line_fn_t nth_line_cb,
|
|
|
|
void *cb_data, long lines, long anchor,
|
|
|
|
long *begin, long *end,
|
|
|
|
const char *path, struct index_state *istate);
|
|
|
|
|
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>
12 years ago
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
|
|
|
|
const char *skip_range_arg(const char *arg, struct index_state *istate);
|
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>
12 years ago
|
|
|
|
|
|
|
#endif /* LINE_RANGE_H */
|