* Basically considers a "box" (off1, off2, lim1, lim2) and scan from both
* the forward diagonal starting from (off1, off2) and the backward diagonal
* starting from (lim1, lim2). If the K values on the same diagonal crosses
- * returns the furthest point of reach. We might end up having to expensive
- * cases using this algorithm is full, so a little bit of heuristic is needed
- * to cut the search and to return a suboptimal point.
+ * returns the furthest point of reach. We might encounter expensive edge cases
+ * using this algorithm, so a little bit of heuristic is needed to cut the
+ * search and to return a suboptimal point.
*/
static long xdl_split(unsigned long const *ha1, long off1, long lim1,
unsigned long const *ha2, long off2, long lim2,
int got_snake = 0;
/*
- * We need to extent the diagonal "domain" by one. If the next
+ * We need to extend the diagonal "domain" by one. If the next
* values exits the box boundaries we need to change it in the
- * opposite direction because (max - min) must be a power of two.
+ * opposite direction because (max - min) must be a power of
+ * two.
+ *
* Also we initialize the external K value to -1 so that we can
- * avoid extra conditions check inside the core loop.
+ * avoid extra conditions in the check inside the core loop.
*/
if (fmin > dmin)
kvdf[--fmin - 1] = -1;
}
/*
- * We need to extent the diagonal "domain" by one. If the next
+ * We need to extend the diagonal "domain" by one. If the next
* values exits the box boundaries we need to change it in the
- * opposite direction because (max - min) must be a power of two.
+ * opposite direction because (max - min) must be a power of
+ * two.
+ *
* Also we initialize the external K value to -1 so that we can
- * avoid extra conditions check inside the core loop.
+ * avoid extra conditions in the check inside the core loop.
*/
if (bmin > dmin)
kvdb[--bmin - 1] = XDL_LINE_MAX;
/*
* If the edit cost is above the heuristic trigger and if
* we got a good snake, we sample current diagonals to see
- * if some of the, have reached an "interesting" path. Our
+ * if some of them have reached an "interesting" path. Our
* measure is a function of the distance from the diagonal
* corner (i1 + i2) penalized with the distance from the
* mid diagonal itself. If this value is above the current
}
/*
- * Enough is enough. We spent too much time here and now we collect
- * the furthest reaching path using the (i1 + i2) measure.
+ * Enough is enough. We spent too much time here and now we
+ * collect the furthest reaching path using the (i1 + i2)
+ * measure.
*/
if (ec >= xenv->mxcost) {
long fbest, fbest1, bbest, bbest1;
/*
- * Rule: "Divide et Impera". Recursively split the box in sub-boxes by calling
- * the box splitting function. Note that the real job (marking changed lines)
- * is done in the two boundary reaching checks.
+ * Rule: "Divide et Impera" (divide & conquer). Recursively split the box in
+ * sub-boxes by calling the box splitting function. Note that the real job
+ * (marking changed lines) is done in the two boundary reaching checks.
*/
int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1,
diffdata_t *dd2, long off2, long lim2,
}
/*
- * Allocate and setup K vectors to be used by the differential algorithm.
+ * Allocate and setup K vectors to be used by the differential
+ * algorithm.
+ *
* One is to store the forward path and one to store the backward path.
*/
ndiags = xe->xdf1.nreff + xe->xdf2.nreff + 3;
/*
* If a line is indented more than this, get_indent() just returns this value.
* This avoids having to do absurd amounts of work for data that are not
- * human-readable text, and also ensures that the output of get_indent fits within
- * an int.
+ * human-readable text, and also ensures that the output of get_indent fits
+ * within an int.
*/
#define MAX_INDENT 200
}
/*
- * If more than this number of consecutive blank rows are found, just return this
- * value. This avoids requiring O(N^2) work for pathological cases, and also
- * ensures that the output of score_split fits in an int.
+ * If more than this number of consecutive blank rows are found, just return
+ * this value. This avoids requiring O(N^2) work for pathological cases, and
+ * also ensures that the output of score_split fits in an int.
*/
#define MAX_BLANKS 20
int end_of_file;
/*
- * How much is the line immediately following the split indented (or -1 if
- * the line is blank):
+ * How much is the line immediately following the split indented (or -1
+ * if the line is blank):
*/
int indent;
int pre_blank;
/*
- * How much is the nearest non-blank line above the split indented (or -1
- * if there is no such line)?
+ * How much is the nearest non-blank line above the split indented (or
+ * -1 if there is no such line)?
*/
int pre_indent;
/*
* Compute a badness score for the hypothetical split whose measurements are
- * stored in m. The weight factors were determined empirically using the tools and
- * corpus described in
+ * stored in m. The weight factors were determined empirically using the tools
+ * and corpus described in
*
* https://github.com/mhagger/diff-slider-tools
*
- * Also see that project if you want to improve the weights based on, for example,
- * a larger or more diverse corpus.
+ * Also see that project if you want to improve the weights based on, for
+ * example, a larger or more diverse corpus.
*/
static void score_add_split(const struct split_measurement *m, struct split_score *s)
{
group_init(xdfo, &go);
while (1) {
- /* If the group is empty in the to-be-compacted file, skip it: */
+ /*
+ * If the group is empty in the to-be-compacted file, skip it:
+ */
if (g.end == g.start)
goto next;
/*
* Now shift the change up and then down as far as possible in
- * each direction. If it bumps into any other changes, merge them.
+ * each direction. If it bumps into any other changes, merge
+ * them.
*/
do {
groupsize = g.end - g.start;
* If the group can be shifted, then we can possibly use this
* freedom to produce a more intuitive diff.
*
- * The group is currently shifted as far down as possible, so the
- * heuristics below only have to handle upwards shifts.
+ * The group is currently shifted as far down as possible, so
+ * the heuristics below only have to handle upwards shifts.
*/
if (g.end == earliest_end) {
/* no shifting was possible */
} else if (end_matching_other != -1) {
/*
- * Move the possibly merged group of changes back to line
- * up with the last group of changes from the other file
- * that it can align with.
+ * Move the possibly merged group of changes back to
+ * line up with the last group of changes from the
+ * other file that it can align with.
*/
while (go.end == go.start) {
if (group_slide_up(xdf, &g, flags))
} else if (flags & XDF_INDENT_HEURISTIC) {
/*
* Indent heuristic: a group of pure add/delete lines
- * implies two splits, one between the end of the "before"
- * context and the start of the group, and another between
- * the end of the group and the beginning of the "after"
- * context. Some splits are aesthetically better and some
- * are worse. We compute a badness "score" for each split,
- * and add the scores for the two splits to define a
- * "score" for each position that the group can be shifted
- * to. Then we pick the shift with the lowest score.
+ * implies two splits, one between the end of the
+ * "before" context and the start of the group, and
+ * another between the end of the group and the
+ * beginning of the "after" context. Some splits are
+ * aesthetically better and some are worse. We compute
+ * a badness "score" for each split, and add the scores
+ * for the two splits to define a "score" for each
+ * position that the group can be shifted to. Then we
+ * pick the shift with the lowest score.
*/
long shift, best_shift = -1;
struct split_score best_score;
projects / thirdparty / git.git / commitdiff
