diff options
Diffstat (limited to 'xdiff')
| -rw-r--r-- | xdiff/xdiff.h | 4 | ||||
| -rw-r--r-- | xdiff/xdiffi.c | 99 | ||||
| -rw-r--r-- | xdiff/xemit.c | 21 | ||||
| -rw-r--r-- | xdiff/xhistogram.c | 2 | ||||
| -rw-r--r-- | xdiff/xinclude.h | 8 | ||||
| -rw-r--r-- | xdiff/xpatience.c | 2 | ||||
| -rw-r--r-- | xdiff/xutils.c | 4 |
7 files changed, 77 insertions, 63 deletions
diff --git a/xdiff/xdiff.h b/xdiff/xdiff.h index b158369020..032e3a9f41 100644 --- a/xdiff/xdiff.h +++ b/xdiff/xdiff.h @@ -113,9 +113,9 @@ typedef struct s_bdiffparam { } bdiffparam_t; -#define xdl_malloc(x) malloc(x) +#define xdl_malloc(x) xmalloc(x) #define xdl_free(ptr) free(ptr) -#define xdl_realloc(ptr,x) realloc(ptr,x) +#define xdl_realloc(ptr,x) xrealloc(ptr,x) void *xdl_mmfile_first(mmfile_t *mmf, long *size); long xdl_mmfile_size(mmfile_t *mmf); diff --git a/xdiff/xdiffi.c b/xdiff/xdiffi.c index 1f1f4a3c78..bd035139f9 100644 --- a/xdiff/xdiffi.c +++ b/xdiff/xdiffi.c @@ -38,9 +38,9 @@ typedef struct s_xdpsplit { * 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, @@ -63,11 +63,13 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1, 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; @@ -98,11 +100,13 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1, } /* - * 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; @@ -138,7 +142,7 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1, /* * 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 @@ -196,8 +200,9 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1, } /* - * 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; @@ -244,9 +249,9 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1, /* - * 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, @@ -323,7 +328,9 @@ int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, } /* - * 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; @@ -394,8 +401,8 @@ static int recs_match(xrecord_t *rec1, xrecord_t *rec2, long flags) /* * 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 @@ -429,9 +436,9 @@ static int get_indent(xrecord_t *rec) } /* - * 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 @@ -443,8 +450,8 @@ struct split_measurement { 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; @@ -454,8 +461,8 @@ struct split_measurement { 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; @@ -581,13 +588,13 @@ static void measure_split(const xdfile_t *xdf, long split, /* * 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) { @@ -809,13 +816,16 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) { 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; @@ -858,17 +868,17 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) { * 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)) @@ -879,14 +889,15 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long 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; diff --git a/xdiff/xemit.c b/xdiff/xemit.c index 7778dc2b19..9d7d6c5087 100644 --- a/xdiff/xemit.c +++ b/xdiff/xemit.c @@ -172,10 +172,12 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, struct func_line func_line = { 0 }; for (xch = xscr; xch; xch = xche->next) { + xdchange_t *xchp = xch; xche = xdl_get_hunk(&xch, xecfg); if (!xch) break; +pre_context_calculation: s1 = XDL_MAX(xch->i1 - xecfg->ctxlen, 0); s2 = XDL_MAX(xch->i2 - xecfg->ctxlen, 0); @@ -210,8 +212,23 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, if (fs1 < 0) fs1 = 0; if (fs1 < s1) { - s2 -= s1 - fs1; + s2 = XDL_MAX(s2 - (s1 - fs1), 0); s1 = fs1; + + /* + * Did we extend context upwards into an + * ignored change? + */ + while (xchp != xch && + xchp->i1 + xchp->chg1 <= s1 && + xchp->i2 + xchp->chg2 <= s2) + xchp = xchp->next; + + /* If so, show it after all. */ + if (xchp != xch) { + xch = xchp; + goto pre_context_calculation; + } } } @@ -232,7 +249,7 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, if (fe1 < 0) fe1 = xe->xdf1.nrec; if (fe1 > e1) { - e2 += fe1 - e1; + e2 = XDL_MIN(e2 + (fe1 - e1), xe->xdf2.nrec); e1 = fe1; } diff --git a/xdiff/xhistogram.c b/xdiff/xhistogram.c index ec85f5992b..c7b35a9667 100644 --- a/xdiff/xhistogram.c +++ b/xdiff/xhistogram.c @@ -42,8 +42,6 @@ */ #include "xinclude.h" -#include "xtypes.h" -#include "xdiff.h" #define MAX_PTR UINT_MAX #define MAX_CNT UINT_MAX diff --git a/xdiff/xinclude.h b/xdiff/xinclude.h index f35c4485df..a4285ac0eb 100644 --- a/xdiff/xinclude.h +++ b/xdiff/xinclude.h @@ -23,13 +23,7 @@ #if !defined(XINCLUDE_H) #define XINCLUDE_H -#include <ctype.h> -#include <stdio.h> -#include <stdlib.h> -#include <unistd.h> -#include <string.h> -#include <limits.h> - +#include "git-compat-util.h" #include "xmacros.h" #include "xdiff.h" #include "xtypes.h" diff --git a/xdiff/xpatience.c b/xdiff/xpatience.c index f3573d9f00..3c5601b602 100644 --- a/xdiff/xpatience.c +++ b/xdiff/xpatience.c @@ -20,8 +20,6 @@ * */ #include "xinclude.h" -#include "xtypes.h" -#include "xdiff.h" /* * The basic idea of patience diff is to find lines that are unique in diff --git a/xdiff/xutils.c b/xdiff/xutils.c index 963e1c58b9..cfa6e2220f 100644 --- a/xdiff/xutils.c +++ b/xdiff/xutils.c @@ -20,13 +20,9 @@ * */ -#include <limits.h> -#include <assert.h> #include "xinclude.h" - - long xdl_bogosqrt(long n) { long i; |