diff options
Diffstat (limited to 'xdiff')
| -rw-r--r-- | xdiff/xdiff.h | 22 | ||||
| -rw-r--r-- | xdiff/xdiffi.c | 641 | ||||
| -rw-r--r-- | xdiff/xdiffi.h | 3 | ||||
| -rw-r--r-- | xdiff/xemit.c | 212 | ||||
| -rw-r--r-- | xdiff/xemit.h | 2 | ||||
| -rw-r--r-- | xdiff/xhistogram.c | 363 | ||||
| -rw-r--r-- | xdiff/xmerge.c | 107 | ||||
| -rw-r--r-- | xdiff/xpatience.c | 33 | ||||
| -rw-r--r-- | xdiff/xprepare.c | 223 | ||||
| -rw-r--r-- | xdiff/xutils.c | 117 | ||||
| -rw-r--r-- | xdiff/xutils.h | 8 |
11 files changed, 1364 insertions, 367 deletions
diff --git a/xdiff/xdiff.h b/xdiff/xdiff.h index 711048ea36..b090ad8eac 100644 --- a/xdiff/xdiff.h +++ b/xdiff/xdiff.h @@ -32,16 +32,19 @@ extern "C" { #define XDF_IGNORE_WHITESPACE (1 << 2) #define XDF_IGNORE_WHITESPACE_CHANGE (1 << 3) #define XDF_IGNORE_WHITESPACE_AT_EOL (1 << 4) -#define XDF_PATIENCE_DIFF (1 << 5) #define XDF_WHITESPACE_FLAGS (XDF_IGNORE_WHITESPACE | XDF_IGNORE_WHITESPACE_CHANGE | XDF_IGNORE_WHITESPACE_AT_EOL) -#define XDL_PATCH_NORMAL '-' -#define XDL_PATCH_REVERSE '+' -#define XDL_PATCH_MODEMASK ((1 << 8) - 1) -#define XDL_PATCH_IGNOREBSPACE (1 << 8) +#define XDF_PATIENCE_DIFF (1 << 5) +#define XDF_HISTOGRAM_DIFF (1 << 6) +#define XDF_DIFF_ALGORITHM_MASK (XDF_PATIENCE_DIFF | XDF_HISTOGRAM_DIFF) +#define XDF_DIFF_ALG(x) ((x) & XDF_DIFF_ALGORITHM_MASK) + +#define XDF_IGNORE_BLANK_LINES (1 << 7) + +#define XDF_INDENT_HEURISTIC (1 << 8) #define XDL_EMIT_FUNCNAMES (1 << 0) -#define XDL_EMIT_COMMON (1 << 1) +#define XDL_EMIT_FUNCCONTEXT (1 << 2) #define XDL_MMB_READONLY (1 << 0) @@ -86,13 +89,17 @@ typedef struct s_xdemitcb { typedef long (*find_func_t)(const char *line, long line_len, char *buffer, long buffer_size, void *priv); +typedef int (*xdl_emit_hunk_consume_func_t)(long start_a, long count_a, + long start_b, long count_b, + void *cb_data); + typedef struct s_xdemitconf { long ctxlen; long interhunkctxlen; unsigned long flags; find_func_t find_func; void *find_func_priv; - void (*emit_func)(); + xdl_emit_hunk_consume_func_t hunk_func; } xdemitconf_t; typedef struct s_bdiffparam { @@ -105,7 +112,6 @@ typedef struct s_bdiffparam { #define xdl_realloc(ptr,x) realloc(ptr,x) void *xdl_mmfile_first(mmfile_t *mmf, long *size); -void *xdl_mmfile_next(mmfile_t *mmf, long *size); long xdl_mmfile_size(mmfile_t *mmf); int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, diff --git a/xdiff/xdiffi.c b/xdiff/xdiffi.c index da67c04357..93a65680a1 100644 --- a/xdiff/xdiffi.c +++ b/xdiff/xdiffi.c @@ -328,9 +328,12 @@ int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, xdalgoenv_t xenv; diffdata_t dd1, dd2; - if (xpp->flags & XDF_PATIENCE_DIFF) + if (XDF_DIFF_ALG(xpp->flags) == XDF_PATIENCE_DIFF) return xdl_do_patience_diff(mf1, mf2, xpp, xe); + if (XDF_DIFF_ALG(xpp->flags) == XDF_HISTOGRAM_DIFF) + return xdl_do_histogram_diff(mf1, mf2, xpp, xe); + if (xdl_prepare_env(mf1, mf2, xpp, xe) < 0) { return -1; @@ -391,111 +394,550 @@ static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1, xch->i2 = i2; xch->chg1 = chg1; xch->chg2 = chg2; + xch->ignore = 0; return xch; } -int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) { - long ix, ixo, ixs, ixref, grpsiz, nrec = xdf->nrec; - char *rchg = xdf->rchg, *rchgo = xdfo->rchg; - xrecord_t **recs = xdf->recs; +static int recs_match(xrecord_t *rec1, xrecord_t *rec2, long flags) +{ + return (rec1->ha == rec2->ha && + xdl_recmatch(rec1->ptr, rec1->size, + rec2->ptr, rec2->size, + 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. + */ +#define MAX_INDENT 200 + +/* + * Return the amount of indentation of the specified line, treating TAB as 8 + * columns. Return -1 if line is empty or contains only whitespace. Clamp the + * output value at MAX_INDENT. + */ +static int get_indent(xrecord_t *rec) +{ + long i; + int ret = 0; + + for (i = 0; i < rec->size; i++) { + char c = rec->ptr[i]; + + if (!XDL_ISSPACE(c)) + return ret; + else if (c == ' ') + ret += 1; + else if (c == '\t') + ret += 8 - ret % 8; + /* ignore other whitespace characters */ + + if (ret >= MAX_INDENT) + return MAX_INDENT; + } + + /* The line contains only whitespace. */ + return -1; +} +/* + * 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 + +/* Characteristics measured about a hypothetical split position. */ +struct split_measurement { /* - * This is the same of what GNU diff does. Move back and forward - * change groups for a consistent and pretty diff output. This also - * helps in finding joinable change groups and reduce the diff size. + * Is the split at the end of the file (aside from any blank lines)? */ - for (ix = ixo = 0;;) { - /* - * Find the first changed line in the to-be-compacted file. - * We need to keep track of both indexes, so if we find a - * changed lines group on the other file, while scanning the - * to-be-compacted file, we need to skip it properly. Note - * that loops that are testing for changed lines on rchg* do - * not need index bounding since the array is prepared with - * a zero at position -1 and N. - */ - for (; ix < nrec && !rchg[ix]; ix++) - while (rchgo[ixo++]); - if (ix == nrec) + int end_of_file; + + /* + * How much is the line immediately following the split indented (or -1 if + * the line is blank): + */ + int indent; + + /* + * How many consecutive lines above the split are blank? + */ + int pre_blank; + + /* + * How much is the nearest non-blank line above the split indented (or -1 + * if there is no such line)? + */ + int pre_indent; + + /* + * How many lines after the line following the split are blank? + */ + int post_blank; + + /* + * How much is the nearest non-blank line after the line following the + * split indented (or -1 if there is no such line)? + */ + int post_indent; +}; + +struct split_score { + /* The effective indent of this split (smaller is preferred). */ + int effective_indent; + + /* Penalty for this split (smaller is preferred). */ + int penalty; +}; + +/* + * Fill m with information about a hypothetical split of xdf above line split. + */ +static void measure_split(const xdfile_t *xdf, long split, + struct split_measurement *m) +{ + long i; + + if (split >= xdf->nrec) { + m->end_of_file = 1; + m->indent = -1; + } else { + m->end_of_file = 0; + m->indent = get_indent(xdf->recs[split]); + } + + m->pre_blank = 0; + m->pre_indent = -1; + for (i = split - 1; i >= 0; i--) { + m->pre_indent = get_indent(xdf->recs[i]); + if (m->pre_indent != -1) + break; + m->pre_blank += 1; + if (m->pre_blank == MAX_BLANKS) { + m->pre_indent = 0; + break; + } + } + + m->post_blank = 0; + m->post_indent = -1; + for (i = split + 1; i < xdf->nrec; i++) { + m->post_indent = get_indent(xdf->recs[i]); + if (m->post_indent != -1) break; + m->post_blank += 1; + if (m->post_blank == MAX_BLANKS) { + m->post_indent = 0; + break; + } + } +} + +/* + * The empirically-determined weight factors used by score_split() below. + * Larger values means that the position is a less favorable place to split. + * + * Note that scores are only ever compared against each other, so multiplying + * all of these weight/penalty values by the same factor wouldn't change the + * heuristic's behavior. Still, we need to set that arbitrary scale *somehow*. + * In practice, these numbers are chosen to be large enough that they can be + * adjusted relative to each other with sufficient precision despite using + * integer math. + */ + +/* Penalty if there are no non-blank lines before the split */ +#define START_OF_FILE_PENALTY 1 + +/* Penalty if there are no non-blank lines after the split */ +#define END_OF_FILE_PENALTY 21 + +/* Multiplier for the number of blank lines around the split */ +#define TOTAL_BLANK_WEIGHT (-30) + +/* Multiplier for the number of blank lines after the split */ +#define POST_BLANK_WEIGHT 6 + +/* + * Penalties applied if the line is indented more than its predecessor + */ +#define RELATIVE_INDENT_PENALTY (-4) +#define RELATIVE_INDENT_WITH_BLANK_PENALTY 10 + +/* + * Penalties applied if the line is indented less than both its predecessor and + * its successor + */ +#define RELATIVE_OUTDENT_PENALTY 24 +#define RELATIVE_OUTDENT_WITH_BLANK_PENALTY 17 + +/* + * Penalties applied if the line is indented less than its predecessor but not + * less than its successor + */ +#define RELATIVE_DEDENT_PENALTY 23 +#define RELATIVE_DEDENT_WITH_BLANK_PENALTY 17 + +/* + * We only consider whether the sum of the effective indents for splits are + * less than (-1), equal to (0), or greater than (+1) each other. The resulting + * value is multiplied by the following weight and combined with the penalty to + * determine the better of two scores. + */ +#define INDENT_WEIGHT 60 + +/* + * 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 + * + * 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. + */ +static void score_add_split(const struct split_measurement *m, struct split_score *s) +{ + /* + * A place to accumulate penalty factors (positive makes this index more + * favored): + */ + int post_blank, total_blank, indent, any_blanks; + + if (m->pre_indent == -1 && m->pre_blank == 0) + s->penalty += START_OF_FILE_PENALTY; + + if (m->end_of_file) + s->penalty += END_OF_FILE_PENALTY; + + /* + * Set post_blank to the number of blank lines following the split, + * including the line immediately after the split: + */ + post_blank = (m->indent == -1) ? 1 + m->post_blank : 0; + total_blank = m->pre_blank + post_blank; + + /* Penalties based on nearby blank lines: */ + s->penalty += TOTAL_BLANK_WEIGHT * total_blank; + s->penalty += POST_BLANK_WEIGHT * post_blank; + + if (m->indent != -1) + indent = m->indent; + else + indent = m->post_indent; + + any_blanks = (total_blank != 0); + /* Note that the effective indent is -1 at the end of the file: */ + s->effective_indent += indent; + + if (indent == -1) { + /* No additional adjustments needed. */ + } else if (m->pre_indent == -1) { + /* No additional adjustments needed. */ + } else if (indent > m->pre_indent) { + /* + * The line is indented more than its predecessor. + */ + s->penalty += any_blanks ? + RELATIVE_INDENT_WITH_BLANK_PENALTY : + RELATIVE_INDENT_PENALTY; + } else if (indent == m->pre_indent) { + /* + * The line has the same indentation level as its predecessor. + * No additional adjustments needed. + */ + } else { /* - * Record the start of a changed-group in the to-be-compacted file - * and find the end of it, on both to-be-compacted and other file - * indexes (ix and ixo). + * The line is indented less than its predecessor. It could be + * the block terminator of the previous block, but it could + * also be the start of a new block (e.g., an "else" block, or + * maybe the previous block didn't have a block terminator). + * Try to distinguish those cases based on what comes next: */ - ixs = ix; - for (ix++; rchg[ix]; ix++); - for (; rchgo[ixo]; ixo++); + if (m->post_indent != -1 && m->post_indent > indent) { + /* + * The following line is indented more. So it is likely + * that this line is the start of a block. + */ + s->penalty += any_blanks ? + RELATIVE_OUTDENT_WITH_BLANK_PENALTY : + RELATIVE_OUTDENT_PENALTY; + } else { + /* + * That was probably the end of a block. + */ + s->penalty += any_blanks ? + RELATIVE_DEDENT_WITH_BLANK_PENALTY : + RELATIVE_DEDENT_PENALTY; + } + } +} + +static int score_cmp(struct split_score *s1, struct split_score *s2) +{ + /* -1 if s1.effective_indent < s2->effective_indent, etc. */ + int cmp_indents = ((s1->effective_indent > s2->effective_indent) - + (s1->effective_indent < s2->effective_indent)); + + return INDENT_WEIGHT * cmp_indents + (s1->penalty - s2->penalty); +} + +/* + * Represent a group of changed lines in an xdfile_t (i.e., a contiguous group + * of lines that was inserted or deleted from the corresponding version of the + * file). We consider there to be such a group at the beginning of the file, at + * the end of the file, and between any two unchanged lines, though most such + * groups will usually be empty. + * + * If the first line in a group is equal to the line following the group, then + * the group can be slid down. Similarly, if the last line in a group is equal + * to the line preceding the group, then the group can be slid up. See + * group_slide_down() and group_slide_up(). + * + * Note that loops that are testing for changed lines in xdf->rchg do not need + * index bounding since the array is prepared with a zero at position -1 and N. + */ +struct xdlgroup { + /* + * The index of the first changed line in the group, or the index of + * the unchanged line above which the (empty) group is located. + */ + long start; + + /* + * The index of the first unchanged line after the group. For an empty + * group, end is equal to start. + */ + long end; +}; + +/* + * Initialize g to point at the first group in xdf. + */ +static void group_init(xdfile_t *xdf, struct xdlgroup *g) +{ + g->start = g->end = 0; + while (xdf->rchg[g->end]) + g->end++; +} + +/* + * Move g to describe the next (possibly empty) group in xdf and return 0. If g + * is already at the end of the file, do nothing and return -1. + */ +static inline int group_next(xdfile_t *xdf, struct xdlgroup *g) +{ + if (g->end == xdf->nrec) + return -1; + + g->start = g->end + 1; + for (g->end = g->start; xdf->rchg[g->end]; g->end++) + ; + + return 0; +} + +/* + * Move g to describe the previous (possibly empty) group in xdf and return 0. + * If g is already at the beginning of the file, do nothing and return -1. + */ +static inline int group_previous(xdfile_t *xdf, struct xdlgroup *g) +{ + if (g->start == 0) + return -1; + + g->end = g->start - 1; + for (g->start = g->end; xdf->rchg[g->start - 1]; g->start--) + ; + + return 0; +} + +/* + * If g can be slid toward the end of the file, do so, and if it bumps into a + * following group, expand this group to include it. Return 0 on success or -1 + * if g cannot be slid down. + */ +static int group_slide_down(xdfile_t *xdf, struct xdlgroup *g, long flags) +{ + if (g->end < xdf->nrec && + recs_match(xdf->recs[g->start], xdf->recs[g->end], flags)) { + xdf->rchg[g->start++] = 0; + xdf->rchg[g->end++] = 1; + + while (xdf->rchg[g->end]) + g->end++; + + return 0; + } else { + return -1; + } +} + +/* + * If g can be slid toward the beginning of the file, do so, and if it bumps + * into a previous group, expand this group to include it. Return 0 on success + * or -1 if g cannot be slid up. + */ +static int group_slide_up(xdfile_t *xdf, struct xdlgroup *g, long flags) +{ + if (g->start > 0 && + recs_match(xdf->recs[g->start - 1], xdf->recs[g->end - 1], flags)) { + xdf->rchg[--g->start] = 1; + xdf->rchg[--g->end] = 0; + + while (xdf->rchg[g->start - 1]) + g->start--; + + return 0; + } else { + return -1; + } +} + +static void xdl_bug(const char *msg) +{ + fprintf(stderr, "BUG: %s\n", msg); + exit(1); +} + +/* + * Move back and forward change groups for a consistent and pretty diff output. + * This also helps in finding joinable change groups and reducing the diff + * size. + */ +int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) { + struct xdlgroup g, go; + long earliest_end, end_matching_other; + long groupsize; + + group_init(xdf, &g); + group_init(xdfo, &go); + + while (1) { + /* 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. + */ do { - grpsiz = ix - ixs; + groupsize = g.end - g.start; /* - * If the line before the current change group, is equal to - * the last line of the current change group, shift backward - * the group. + * Keep track of the last "end" index that causes this + * group to align with a group of changed lines in the + * other file. -1 indicates that we haven't found such + * a match yet: */ - while (ixs > 0 && recs[ixs - 1]->ha == recs[ix - 1]->ha && - xdl_recmatch(recs[ixs - 1]->ptr, recs[ixs - 1]->size, recs[ix - 1]->ptr, recs[ix - 1]->size, flags)) { - rchg[--ixs] = 1; - rchg[--ix] = 0; - - /* - * This change might have joined two change groups, - * so we try to take this scenario in account by moving - * the start index accordingly (and so the other-file - * end-of-group index). - */ - for (; rchg[ixs - 1]; ixs--); - while (rchgo[--ixo]); - } + end_matching_other = -1; - /* - * Record the end-of-group position in case we are matched - * with a group of changes in the other file (that is, the - * change record before the end-of-group index in the other - * file is set). - */ - ixref = rchgo[ixo - 1] ? ix: nrec; + /* Shift the group backward as much as possible: */ + while (!group_slide_up(xdf, &g, flags)) + if (group_previous(xdfo, &go)) + xdl_bug("group sync broken sliding up"); /* - * If the first line of the current change group, is equal to - * the line next of the current change group, shift forward - * the group. + * This is this highest that this group can be shifted. + * Record its end index: */ - while (ix < nrec && recs[ixs]->ha == recs[ix]->ha && - xdl_recmatch(recs[ixs]->ptr, recs[ixs]->size, recs[ix]->ptr, recs[ix]->size, flags)) { - rchg[ixs++] = 0; - rchg[ix++] = 1; - - /* - * This change might have joined two change groups, - * so we try to take this scenario in account by moving - * the start index accordingly (and so the other-file - * end-of-group index). Keep tracking the reference - * index in case we are shifting together with a - * corresponding group of changes in the other file. - */ - for (; rchg[ix]; ix++); - while (rchgo[++ixo]) - ixref = ix; + earliest_end = g.end; + + if (go.end > go.start) + end_matching_other = g.end; + + /* Now shift the group forward as far as possible: */ + while (1) { + if (group_slide_down(xdf, &g, flags)) + break; + if (group_next(xdfo, &go)) + xdl_bug("group sync broken sliding down"); + + if (go.end > go.start) + end_matching_other = g.end; } - } while (grpsiz != ix - ixs); + } while (groupsize != g.end - g.start); /* - * Try to move back the possibly merged group of changes, to match - * the recorded postion in the other file. + * 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. */ - while (ixref < ix) { - rchg[--ixs] = 1; - rchg[--ix] = 0; - while (rchgo[--ixo]); + + 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. + */ + while (go.end == go.start) { + if (group_slide_up(xdf, &g, flags)) + xdl_bug("match disappeared"); + if (group_previous(xdfo, &go)) + xdl_bug("group sync broken sliding to match"); + } + } 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. + */ + long shift, best_shift = -1; + struct split_score best_score; + + for (shift = earliest_end; shift <= g.end; shift++) { + struct split_measurement m; + struct split_score score = {0, 0}; + + measure_split(xdf, shift, &m); + score_add_split(&m, &score); + measure_split(xdf, shift - groupsize, &m); + score_add_split(&m, &score); + if (best_shift == -1 || + score_cmp(&score, &best_score) <= 0) { + best_score.effective_indent = score.effective_indent; + best_score.penalty = score.penalty; + best_shift = shift; + } + } + + while (g.end > best_shift) { + if (group_slide_up(xdf, &g, flags)) + xdl_bug("best shift unreached"); + if (group_previous(xdfo, &go)) + xdl_bug("group sync broken sliding to blank line"); + } } + + next: + /* Move past the just-processed group: */ + if (group_next(xdf, &g)) + break; + if (group_next(xdfo, &go)) + xdl_bug("group sync broken moving to next group"); } + if (!group_next(xdfo, &go)) + xdl_bug("group sync broken at end of file"); + return 0; } @@ -535,13 +977,49 @@ void xdl_free_script(xdchange_t *xscr) { } } +static int xdl_call_hunk_func(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, + xdemitconf_t const *xecfg) +{ + xdchange_t *xch, *xche; + + for (xch = xscr; xch; xch = xche->next) { + xche = xdl_get_hunk(&xch, xecfg); + if (!xch) + break; + if (xecfg->hunk_func(xch->i1, xche->i1 + xche->chg1 - xch->i1, + xch->i2, xche->i2 + xche->chg2 - xch->i2, + ecb->priv) < 0) + return -1; + } + return 0; +} + +static void xdl_mark_ignorable(xdchange_t *xscr, xdfenv_t *xe, long flags) +{ + xdchange_t *xch; + + for (xch = xscr; xch; xch = xch->next) { + int ignore = 1; + xrecord_t **rec; + long i; + + rec = &xe->xdf1.recs[xch->i1]; + for (i = 0; i < xch->chg1 && ignore; i++) + ignore = xdl_blankline(rec[i]->ptr, rec[i]->size, flags); + + rec = &xe->xdf2.recs[xch->i2]; + for (i = 0; i < xch->chg2 && ignore; i++) + ignore = xdl_blankline(rec[i]->ptr, rec[i]->size, flags); + + xch->ignore = ignore; + } +} int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, xdemitconf_t const *xecfg, xdemitcb_t *ecb) { xdchange_t *xscr; xdfenv_t xe; - emit_func_t ef = xecfg->emit_func ? - (emit_func_t)xecfg->emit_func : xdl_emit_diff; + emit_func_t ef = xecfg->hunk_func ? xdl_call_hunk_func : xdl_emit_diff; if (xdl_do_diff(mf1, mf2, xpp, &xe) < 0) { @@ -555,6 +1033,9 @@ int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, return -1; } if (xscr) { + if (xpp->flags & XDF_IGNORE_BLANK_LINES) + xdl_mark_ignorable(xscr, &xe, xpp->flags); + if (ef(&xe, xscr, ecb, xecfg) < 0) { xdl_free_script(xscr); diff --git a/xdiff/xdiffi.h b/xdiff/xdiffi.h index ad033a8e6a..8b81206c9a 100644 --- a/xdiff/xdiffi.h +++ b/xdiff/xdiffi.h @@ -41,6 +41,7 @@ typedef struct s_xdchange { struct s_xdchange *next; long i1, i2; long chg1, chg2; + int ignore; } xdchange_t; @@ -57,5 +58,7 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, xdemitconf_t const *xecfg); int xdl_do_patience_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, xdfenv_t *env); +int xdl_do_histogram_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, + xdfenv_t *env); #endif /* #if !defined(XDIFFI_H) */ diff --git a/xdiff/xemit.c b/xdiff/xemit.c index 277e2eec5b..8c88dbde38 100644 --- a/xdiff/xemit.c +++ b/xdiff/xemit.c @@ -22,15 +22,6 @@ #include "xinclude.h" - - - -static long xdl_get_rec(xdfile_t *xdf, long ri, char const **rec); -static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t *ecb); - - - - static long xdl_get_rec(xdfile_t *xdf, long ri, char const **rec) { *rec = xdf->recs[ri]->ptr; @@ -56,16 +47,51 @@ static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t * /* * Starting at the passed change atom, find the latest change atom to be included * inside the differential hunk according to the specified configuration. + * Also advance xscr if the first changes must be discarded. */ -xdchange_t *xdl_get_hunk(xdchange_t *xscr, xdemitconf_t const *xecfg) { - xdchange_t *xch, *xchp; +xdchange_t *xdl_get_hunk(xdchange_t **xscr, xdemitconf_t const *xecfg) +{ + xdchange_t *xch, *xchp, *lxch; long max_common = 2 * xecfg->ctxlen + xecfg->interhunkctxlen; + long max_ignorable = xecfg->ctxlen; + unsigned long ignored = 0; /* number of ignored blank lines */ + + /* remove ignorable changes that are too far before other changes */ + for (xchp = *xscr; xchp && xchp->ignore; xchp = xchp->next) { + xch = xchp->next; + + if (xch == NULL || + xch->i1 - (xchp->i1 + xchp->chg1) >= max_ignorable) + *xscr = xch; + } + + if (*xscr == NULL) + return NULL; + + lxch = *xscr; - for (xchp = xscr, xch = xscr->next; xch; xchp = xch, xch = xch->next) - if (xch->i1 - (xchp->i1 + xchp->chg1) > max_common) + for (xchp = *xscr, xch = xchp->next; xch; xchp = xch, xch = xch->next) { + long distance = xch->i1 - (xchp->i1 + xchp->chg1); + if (distance > max_common) break; - return xchp; + if (distance < max_ignorable && (!xch->ignore || lxch == xchp)) { + lxch = xch; + ignored = 0; + } else if (distance < max_ignorable && xch->ignore) { + ignored += xch->chg2; + } else if (lxch != xchp && + xch->i1 + ignored - (lxch->i1 + lxch->chg1) > max_common) { + break; + } else if (!xch->ignore) { + lxch = xch; + ignored = 0; + } else { + ignored += xch->chg2; + } + } + + return lxch; } @@ -73,7 +99,7 @@ static long def_ff(const char *rec, long len, char *buf, long sz, void *priv) { if (len > 0 && (isalpha((unsigned char)*rec) || /* identifier? */ - *rec == '_' || /* also identifier? */ + *rec == '_' || /* also identifier? */ *rec == '$')) { /* identifiers from VMS and other esoterico */ if (len > sz) len = sz; @@ -85,39 +111,104 @@ static long def_ff(const char *rec, long len, char *buf, long sz, void *priv) return -1; } -static int xdl_emit_common(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, - xdemitconf_t const *xecfg) { - xdfile_t *xdf = &xe->xdf1; - const char *rchg = xdf->rchg; - long ix; +static long match_func_rec(xdfile_t *xdf, xdemitconf_t const *xecfg, long ri, + char *buf, long sz) +{ + const char *rec; + long len = xdl_get_rec(xdf, ri, &rec); + if (!xecfg->find_func) + return def_ff(rec, len, buf, sz, xecfg->find_func_priv); + return xecfg->find_func(rec, len, buf, sz, xecfg->find_func_priv); +} + +struct func_line { + long len; + char buf[80]; +}; - for (ix = 0; ix < xdf->nrec; ix++) { - if (rchg[ix]) - continue; - if (xdl_emit_record(xdf, ix, "", ecb)) - return -1; +static long get_func_line(xdfenv_t *xe, xdemitconf_t const *xecfg, + struct func_line *func_line, long start, long limit) +{ + long l, size, step = (start > limit) ? -1 : 1; + char *buf, dummy[1]; + + buf = func_line ? func_line->buf : dummy; + size = func_line ? sizeof(func_line->buf) : sizeof(dummy); + + for (l = start; l != limit && 0 <= l && l < xe->xdf1.nrec; l += step) { + long len = match_func_rec(&xe->xdf1, xecfg, l, buf, size); + if (len >= 0) { + if (func_line) + func_line->len = len; + return l; + } } - return 0; + return -1; +} + +static int is_empty_rec(xdfile_t *xdf, long ri) +{ + const char *rec; + long len = xdl_get_rec(xdf, ri, &rec); + + while (len > 0 && XDL_ISSPACE(*rec)) { + rec++; + len--; + } + return !len; } int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, xdemitconf_t const *xecfg) { long s1, s2, e1, e2, lctx; xdchange_t *xch, *xche; - char funcbuf[80]; - long funclen = 0; long funclineprev = -1; - find_func_t ff = xecfg->find_func ? xecfg->find_func : def_ff; - - if (xecfg->flags & XDL_EMIT_COMMON) - return xdl_emit_common(xe, xscr, ecb, xecfg); + struct func_line func_line = { 0 }; for (xch = xscr; xch; xch = xche->next) { - xche = xdl_get_hunk(xch, xecfg); + xche = xdl_get_hunk(&xch, xecfg); + if (!xch) + break; s1 = XDL_MAX(xch->i1 - xecfg->ctxlen, 0); s2 = XDL_MAX(xch->i2 - xecfg->ctxlen, 0); + if (xecfg->flags & XDL_EMIT_FUNCCONTEXT) { + long fs1, i1 = xch->i1; + + /* Appended chunk? */ + if (i1 >= xe->xdf1.nrec) { + char dummy[1]; + long i2 = xch->i2; + + /* + * We don't need additional context if + * a whole function was added. + */ + while (i2 < xe->xdf2.nrec) { + if (match_func_rec(&xe->xdf2, xecfg, i2, + dummy, sizeof(dummy)) >= 0) + goto post_context_calculation; + i2++; + } + + /* + * Otherwise get more context from the + * pre-image. + */ + i1 = xe->xdf1.nrec - 1; + } + + fs1 = get_func_line(xe, xecfg, NULL, i1, -1); + if (fs1 < 0) + fs1 = 0; + if (fs1 < s1) { + s2 -= s1 - fs1; + s1 = fs1; + } + } + + post_context_calculation: lctx = xecfg->ctxlen; lctx = XDL_MIN(lctx, xe->xdf1.nrec - (xche->i1 + xche->chg1)); lctx = XDL_MIN(lctx, xe->xdf2.nrec - (xche->i2 + xche->chg2)); @@ -125,34 +216,53 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, e1 = xche->i1 + xche->chg1 + lctx; e2 = xche->i2 + xche->chg2 + lctx; + if (xecfg->flags & XDL_EMIT_FUNCCONTEXT) { + long fe1 = get_func_line(xe, xecfg, NULL, + xche->i1 + xche->chg1, + xe->xdf1.nrec); + while (fe1 > 0 && is_empty_rec(&xe->xdf1, fe1 - 1)) + fe1--; + if (fe1 < 0) + fe1 = xe->xdf1.nrec; + if (fe1 > e1) { + e2 += fe1 - e1; + e1 = fe1; + } + + /* + * Overlap with next change? Then include it + * in the current hunk and start over to find + * its new end. + */ + if (xche->next) { + long l = XDL_MIN(xche->next->i1, + xe->xdf1.nrec - 1); + if (l - xecfg->ctxlen <= e1 || + get_func_line(xe, xecfg, NULL, l, e1) < 0) { + xche = xche->next; + goto post_context_calculation; + } + } + } + /* * Emit current hunk header. */ if (xecfg->flags & XDL_EMIT_FUNCNAMES) { - long l; - for (l = s1 - 1; l >= 0 && l > funclineprev; l--) { - const char *rec; - long reclen = xdl_get_rec(&xe->xdf1, l, &rec); - long newfunclen = ff(rec, reclen, funcbuf, - sizeof(funcbuf), - xecfg->find_func_priv); - if (newfunclen >= 0) { - funclen = newfunclen; - break; - } - } + get_func_line(xe, xecfg, &func_line, + s1 - 1, funclineprev); funclineprev = s1 - 1; } if (xdl_emit_hunk_hdr(s1 + 1, e1 - s1, s2 + 1, e2 - s2, - funcbuf, funclen, ecb) < 0) + func_line.buf, func_line.len, ecb) < 0) return -1; /* * Emit pre-context. */ - for (; s1 < xch->i1; s1++) - if (xdl_emit_record(&xe->xdf1, s1, " ", ecb) < 0) + for (; s2 < xch->i2; s2++) + if (xdl_emit_record(&xe->xdf2, s2, " ", ecb) < 0) return -1; for (s1 = xch->i1, s2 = xch->i2;; xch = xch->next) { @@ -160,7 +270,7 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, * Merge previous with current change atom. */ for (; s1 < xch->i1 && s2 < xch->i2; s1++, s2++) - if (xdl_emit_record(&xe->xdf1, s1, " ", ecb) < 0) + if (xdl_emit_record(&xe->xdf2, s2, " ", ecb) < 0) return -1; /* @@ -186,8 +296,8 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, /* * Emit post-context. */ - for (s1 = xche->i1 + xche->chg1; s1 < e1; s1++) - if (xdl_emit_record(&xe->xdf1, s1, " ", ecb) < 0) + for (s2 = xche->i2 + xche->chg2; s2 < e2; s2++) + if (xdl_emit_record(&xe->xdf2, s2, " ", ecb) < 0) return -1; } diff --git a/xdiff/xemit.h b/xdiff/xemit.h index c2e2e83027..d29710770c 100644 --- a/xdiff/xemit.h +++ b/xdiff/xemit.h @@ -27,7 +27,7 @@ typedef int (*emit_func_t)(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, xdemitconf_t const *xecfg); -xdchange_t *xdl_get_hunk(xdchange_t *xscr, xdemitconf_t const *xecfg); +xdchange_t *xdl_get_hunk(xdchange_t **xscr, xdemitconf_t const *xecfg); int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, xdemitconf_t const *xecfg); diff --git a/xdiff/xhistogram.c b/xdiff/xhistogram.c new file mode 100644 index 0000000000..73210cb6f3 --- /dev/null +++ b/xdiff/xhistogram.c @@ -0,0 +1,363 @@ +/* + * Copyright (C) 2010, Google Inc. + * and other copyright owners as documented in JGit's IP log. + * + * This program and the accompanying materials are made available + * under the terms of the Eclipse Distribution License v1.0 which + * accompanies this distribution, is reproduced below, and is + * available at http://www.eclipse.org/org/documents/edl-v10.php + * + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials provided + * with the distribution. + * + * - Neither the name of the Eclipse Foundation, Inc. nor the + * names of its contributors may be used to endorse or promote + * products derived from this software without specific prior + * written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND + * CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, + * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES + * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR + * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT + * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER + * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, + * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include "xinclude.h" +#include "xtypes.h" +#include "xdiff.h" + +#define MAX_PTR UINT_MAX +#define MAX_CNT UINT_MAX + +#define LINE_END(n) (line##n + count##n - 1) +#define LINE_END_PTR(n) (*line##n + *count##n - 1) + +struct histindex { + struct record { + unsigned int ptr, cnt; + struct record *next; + } **records, /* an occurrence */ + **line_map; /* map of line to record chain */ + chastore_t rcha; + unsigned int *next_ptrs; + unsigned int table_bits, + records_size, + line_map_size; + + unsigned int max_chain_length, + key_shift, + ptr_shift; + + unsigned int cnt, + has_common; + + xdfenv_t *env; + xpparam_t const *xpp; +}; + +struct region { + unsigned int begin1, end1; + unsigned int begin2, end2; +}; + +#define LINE_MAP(i, a) (i->line_map[(a) - i->ptr_shift]) + +#define NEXT_PTR(index, ptr) \ + (index->next_ptrs[(ptr) - index->ptr_shift]) + +#define CNT(index, ptr) \ + ((LINE_MAP(index, ptr))->cnt) + +#define REC(env, s, l) \ + (env->xdf##s.recs[l - 1]) + +static int cmp_recs(xpparam_t const *xpp, + xrecord_t *r1, xrecord_t *r2) +{ + return r1->ha == r2->ha && + xdl_recmatch(r1->ptr, r1->size, r2->ptr, r2->size, + xpp->flags); +} + +#define CMP_ENV(xpp, env, s1, l1, s2, l2) \ + (cmp_recs(xpp, REC(env, s1, l1), REC(env, s2, l2))) + +#define CMP(i, s1, l1, s2, l2) \ + (cmp_recs(i->xpp, REC(i->env, s1, l1), REC(i->env, s2, l2))) + +#define TABLE_HASH(index, side, line) \ + XDL_HASHLONG((REC(index->env, side, line))->ha, index->table_bits) + +static int scanA(struct histindex *index, int line1, int count1) +{ + unsigned int ptr, tbl_idx; + unsigned int chain_len; + struct record **rec_chain, *rec; + + for (ptr = LINE_END(1); line1 <= ptr; ptr--) { + tbl_idx = TABLE_HASH(index, 1, ptr); + rec_chain = index->records + tbl_idx; + rec = *rec_chain; + + chain_len = 0; + while (rec) { + if (CMP(index, 1, rec->ptr, 1, ptr)) { + /* + * ptr is identical to another element. Insert + * it onto the front of the existing element + * chain. + */ + NEXT_PTR(index, ptr) = rec->ptr; + rec->ptr = ptr; + /* cap rec->cnt at MAX_CNT */ + rec->cnt = XDL_MIN(MAX_CNT, rec->cnt + 1); + LINE_MAP(index, ptr) = rec; + goto continue_scan; + } + + rec = rec->next; + chain_len++; + } + + if (chain_len == index->max_chain_length) + return -1; + + /* + * This is the first time we have ever seen this particular + * element in the sequence. Construct a new chain for it. + */ + if (!(rec = xdl_cha_alloc(&index->rcha))) + return -1; + rec->ptr = ptr; + rec->cnt = 1; + rec->next = *rec_chain; + *rec_chain = rec; + LINE_MAP(index, ptr) = rec; + +continue_scan: + ; /* no op */ + } + + return 0; +} + +static int try_lcs(struct histindex *index, struct region *lcs, int b_ptr, + int line1, int count1, int line2, int count2) +{ + unsigned int b_next = b_ptr + 1; + struct record *rec = index->records[TABLE_HASH(index, 2, b_ptr)]; + unsigned int as, ae, bs, be, np, rc; + int should_break; + + for (; rec; rec = rec->next) { + if (rec->cnt > index->cnt) { + if (!index->has_common) + index->has_common = CMP(index, 1, rec->ptr, 2, b_ptr); + continue; + } + + as = rec->ptr; + if (!CMP(index, 1, as, 2, b_ptr)) + continue; + + index->has_common = 1; + for (;;) { + should_break = 0; + np = NEXT_PTR(index, as); + bs = b_ptr; + ae = as; + be = bs; + rc = rec->cnt; + + while (line1 < as && line2 < bs + && CMP(index, 1, as - 1, 2, bs - 1)) { + as--; + bs--; + if (1 < rc) + rc = XDL_MIN(rc, CNT(index, as)); + } + while (ae < LINE_END(1) && be < LINE_END(2) + && CMP(index, 1, ae + 1, 2, be + 1)) { + ae++; + be++; + if (1 < rc) + rc = XDL_MIN(rc, CNT(index, ae)); + } + + if (b_next <= be) + b_next = be + 1; + if (lcs->end1 - lcs->begin1 < ae - as || rc < index->cnt) { + lcs->begin1 = as; + lcs->begin2 = bs; + lcs->end1 = ae; + lcs->end2 = be; + index->cnt = rc; + } + + if (np == 0) + break; + + while (np <= ae) { + np = NEXT_PTR(index, np); + if (np == 0) { + should_break = 1; + break; + } + } + + if (should_break) + break; + + as = np; + } + } + return b_next; +} + +static int find_lcs(struct histindex *index, struct region *lcs, + int line1, int count1, int line2, int count2) { + int b_ptr; + + if (scanA(index, line1, count1)) + return -1; + + index->cnt = index->max_chain_length + 1; + + for (b_ptr = line2; b_ptr <= LINE_END(2); ) + b_ptr = try_lcs(index, lcs, b_ptr, line1, count1, line2, count2); + + return index->has_common && index->max_chain_length < index->cnt; +} + +static int fall_back_to_classic_diff(struct histindex *index, + int line1, int count1, int line2, int count2) +{ + xpparam_t xpp; + xpp.flags = index->xpp->flags & ~XDF_DIFF_ALGORITHM_MASK; + + return xdl_fall_back_diff(index->env, &xpp, + line1, count1, line2, count2); +} + +static int histogram_diff(xpparam_t const *xpp, xdfenv_t *env, + int line1, int count1, int line2, int count2) +{ + struct histindex index; + struct region lcs; + int sz; + int result = -1; + + if (count1 <= 0 && count2 <= 0) + return 0; + + if (LINE_END(1) >= MAX_PTR) + return -1; + + if (!count1) { + while(count2--) + env->xdf2.rchg[line2++ - 1] = 1; + return 0; + } else if (!count2) { + while(count1--) + env->xdf1.rchg[line1++ - 1] = 1; + return 0; + } + + memset(&index, 0, sizeof(index)); + + index.env = env; + index.xpp = xpp; + + index.records = NULL; + index.line_map = NULL; + /* in case of early xdl_cha_free() */ + index.rcha.head = NULL; + + index.table_bits = xdl_hashbits(count1); + sz = index.records_size = 1 << index.table_bits; + sz *= sizeof(struct record *); + if (!(index.records = (struct record **) xdl_malloc(sz))) + goto cleanup; + memset(index.records, 0, sz); + + sz = index.line_map_size = count1; + sz *= sizeof(struct record *); + if (!(index.line_map = (struct record **) xdl_malloc(sz))) + goto cleanup; + memset(index.line_map, 0, sz); + + sz = index.line_map_size; + sz *= sizeof(unsigned int); + if (!(index.next_ptrs = (unsigned int *) xdl_malloc(sz))) + goto cleanup; + memset(index.next_ptrs, 0, sz); + + /* lines / 4 + 1 comes from xprepare.c:xdl_prepare_ctx() */ + if (xdl_cha_init(&index.rcha, sizeof(struct record), count1 / 4 + 1) < 0) + goto cleanup; + + index.ptr_shift = line1; + index.max_chain_length = 64; + + memset(&lcs, 0, sizeof(lcs)); + if (find_lcs(&index, &lcs, line1, count1, line2, count2)) + result = fall_back_to_classic_diff(&index, line1, count1, line2, count2); + else { + if (lcs.begin1 == 0 && lcs.begin2 == 0) { + while (count1--) + env->xdf1.rchg[line1++ - 1] = 1; + while (count2--) + env->xdf2.rchg[line2++ - 1] = 1; + result = 0; + } else { + result = histogram_diff(xpp, env, + line1, lcs.begin1 - line1, + line2, lcs.begin2 - line2); + if (result) + goto cleanup; + result = histogram_diff(xpp, env, + lcs.end1 + 1, LINE_END(1) - lcs.end1, + lcs.end2 + 1, LINE_END(2) - lcs.end2); + if (result) + goto cleanup; + } + } + +cleanup: + xdl_free(index.records); + xdl_free(index.line_map); + xdl_free(index.next_ptrs); + xdl_cha_free(&index.rcha); + + return result; +} + +int xdl_do_histogram_diff(mmfile_t *file1, mmfile_t *file2, + xpparam_t const *xpp, xdfenv_t *env) +{ + if (xdl_prepare_env(file1, file2, xpp, env) < 0) + return -1; + + return histogram_diff(xpp, env, + env->xdf1.dstart + 1, env->xdf1.dend - env->xdf1.dstart + 1, + env->xdf2.dstart + 1, env->xdf2.dend - env->xdf2.dstart + 1); +} diff --git a/xdiff/xmerge.c b/xdiff/xmerge.c index 9e13b25abc..f338ad6c75 100644 --- a/xdiff/xmerge.c +++ b/xdiff/xmerge.c @@ -109,7 +109,7 @@ static int xdl_merge_cmp_lines(xdfenv_t *xe1, int i1, xdfenv_t *xe2, int i2, return 0; } -static int xdl_recs_copy_0(int use_orig, xdfenv_t *xe, int i, int count, int add_nl, char *dest) +static int xdl_recs_copy_0(int use_orig, xdfenv_t *xe, int i, int count, int needs_cr, int add_nl, char *dest) { xrecord_t **recs; int size = 0; @@ -125,6 +125,12 @@ static int xdl_recs_copy_0(int use_orig, xdfenv_t *xe, int i, int count, int add if (add_nl) { i = recs[count - 1]->size; if (i == 0 || recs[count - 1]->ptr[i - 1] != '\n') { + if (needs_cr) { + if (dest) + dest[size] = '\r'; + size++; + } + if (dest) dest[size] = '\n'; size++; @@ -133,14 +139,58 @@ static int xdl_recs_copy_0(int use_orig, xdfenv_t *xe, int i, int count, int add return size; } -static int xdl_recs_copy(xdfenv_t *xe, int i, int count, int add_nl, char *dest) +static int xdl_recs_copy(xdfenv_t *xe, int i, int count, int needs_cr, int add_nl, char *dest) +{ + return xdl_recs_copy_0(0, xe, i, count, needs_cr, add_nl, dest); +} + +static int xdl_orig_copy(xdfenv_t *xe, int i, int count, int needs_cr, int add_nl, char *dest) +{ + return xdl_recs_copy_0(1, xe, i, count, needs_cr, add_nl, dest); +} + +/* + * Returns 1 if the i'th line ends in CR/LF (if it is the last line and + * has no eol, the preceding line, if any), 0 if it ends in LF-only, and + * -1 if the line ending cannot be determined. + */ +static int is_eol_crlf(xdfile_t *file, int i) { - return xdl_recs_copy_0(0, xe, i, count, add_nl, dest); + long size; + + if (i < file->nrec - 1) + /* All lines before the last *must* end in LF */ + return (size = file->recs[i]->size) > 1 && + file->recs[i]->ptr[size - 2] == '\r'; + if (!file->nrec) + /* Cannot determine eol style from empty file */ + return -1; + if ((size = file->recs[i]->size) && + file->recs[i]->ptr[size - 1] == '\n') + /* Last line; ends in LF; Is it CR/LF? */ + return size > 1 && + file->recs[i]->ptr[size - 2] == '\r'; + if (!i) + /* The only line has no eol */ + return -1; + /* Determine eol from second-to-last line */ + return (size = file->recs[i - 1]->size) > 1 && + file->recs[i - 1]->ptr[size - 2] == '\r'; } -static int xdl_orig_copy(xdfenv_t *xe, int i, int count, int add_nl, char *dest) +static int is_cr_needed(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m) { - return xdl_recs_copy_0(1, xe, i, count, add_nl, dest); + int needs_cr; + + /* Match post-images' preceding, or first, lines' end-of-line style */ + needs_cr = is_eol_crlf(&xe1->xdf2, m->i1 ? m->i1 - 1 : 0); + if (needs_cr) + needs_cr = is_eol_crlf(&xe2->xdf2, m->i2 ? m->i2 - 1 : 0); + /* Look at pre-image's first line, unless we already settled on LF */ + if (needs_cr) + needs_cr = is_eol_crlf(&xe1->xdf1, 0); + /* If still undecided, use LF-only */ + return needs_cr < 0 ? 0 : needs_cr; } static int fill_conflict_hunk(xdfenv_t *xe1, const char *name1, @@ -152,16 +202,17 @@ static int fill_conflict_hunk(xdfenv_t *xe1, const char *name1, int marker1_size = (name1 ? strlen(name1) + 1 : 0); int marker2_size = (name2 ? strlen(name2) + 1 : 0); int marker3_size = (name3 ? strlen(name3) + 1 : 0); + int needs_cr = is_cr_needed(xe1, xe2, m); if (marker_size <= 0) marker_size = DEFAULT_CONFLICT_MARKER_SIZE; /* Before conflicting part */ - size += xdl_recs_copy(xe1, i, m->i1 - i, 0, + size += xdl_recs_copy(xe1, i, m->i1 - i, 0, 0, dest ? dest + size : NULL); if (!dest) { - size += marker_size + 1 + marker1_size; + size += marker_size + 1 + needs_cr + marker1_size; } else { memset(dest + size, '<', marker_size); size += marker_size; @@ -170,17 +221,19 @@ static int fill_conflict_hunk(xdfenv_t *xe1, const char *name1, memcpy(dest + size + 1, name1, marker1_size - 1); size += marker1_size; } + if (needs_cr) + dest[size++] = '\r'; dest[size++] = '\n'; } /* Postimage from side #1 */ - size += xdl_recs_copy(xe1, m->i1, m->chg1, 1, + size += xdl_recs_copy(xe1, m->i1, m->chg1, needs_cr, 1, dest ? dest + size : NULL); if (style == XDL_MERGE_DIFF3) { /* Shared preimage */ if (!dest) { - size += marker_size + 1 + marker3_size; + size += marker_size + 1 + needs_cr + marker3_size; } else { memset(dest + size, '|', marker_size); size += marker_size; @@ -189,25 +242,29 @@ static int fill_conflict_hunk(xdfenv_t *xe1, const char *name1, memcpy(dest + size + 1, name3, marker3_size - 1); size += marker3_size; } + if (needs_cr) + dest[size++] = '\r'; dest[size++] = '\n'; } - size += xdl_orig_copy(xe1, m->i0, m->chg0, 1, + size += xdl_orig_copy(xe1, m->i0, m->chg0, needs_cr, 1, dest ? dest + size : NULL); } if (!dest) { - size += marker_size + 1; + size += marker_size + 1 + needs_cr; } else { memset(dest + size, '=', marker_size); size += marker_size; + if (needs_cr) + dest[size++] = '\r'; dest[size++] = '\n'; } /* Postimage from side #2 */ - size += xdl_recs_copy(xe2, m->i2, m->chg2, 1, + size += xdl_recs_copy(xe2, m->i2, m->chg2, needs_cr, 1, dest ? dest + size : NULL); if (!dest) { - size += marker_size + 1 + marker2_size; + size += marker_size + 1 + needs_cr + marker2_size; } else { memset(dest + size, '>', marker_size); size += marker_size; @@ -216,6 +273,8 @@ static int fill_conflict_hunk(xdfenv_t *xe1, const char *name1, memcpy(dest + size + 1, name2, marker2_size - 1); size += marker2_size; } + if (needs_cr) + dest[size++] = '\r'; dest[size++] = '\n'; } return size; @@ -241,21 +300,24 @@ static int xdl_fill_merge_buffer(xdfenv_t *xe1, const char *name1, marker_size); else if (m->mode & 3) { /* Before conflicting part */ - size += xdl_recs_copy(xe1, i, m->i1 - i, 0, + size += xdl_recs_copy(xe1, i, m->i1 - i, 0, 0, dest ? dest + size : NULL); /* Postimage from side #1 */ - if (m->mode & 1) - size += xdl_recs_copy(xe1, m->i1, m->chg1, 1, + if (m->mode & 1) { + int needs_cr = is_cr_needed(xe1, xe2, m); + + size += xdl_recs_copy(xe1, m->i1, m->chg1, needs_cr, (m->mode & 2), dest ? dest + size : NULL); + } /* Postimage from side #2 */ if (m->mode & 2) - size += xdl_recs_copy(xe2, m->i2, m->chg2, 1, + size += xdl_recs_copy(xe2, m->i2, m->chg2, 0, 0, dest ? dest + size : NULL); } else continue; i = m->i1 + m->chg1; } - size += xdl_recs_copy(xe1, i, xe1->xdf2.nrec - i, 0, + size += xdl_recs_copy(xe1, i, xe1->xdf2.nrec - i, 0, 0, dest ? dest + size : NULL); return size; } @@ -579,8 +641,11 @@ int xdl_merge(mmfile_t *orig, mmfile_t *mf1, mmfile_t *mf2, result->ptr = NULL; result->size = 0; - if (xdl_do_diff(orig, mf1, xpp, &xe1) < 0 || - xdl_do_diff(orig, mf2, xpp, &xe2) < 0) { + if (xdl_do_diff(orig, mf1, xpp, &xe1) < 0) { + return -1; + } + if (xdl_do_diff(orig, mf2, xpp, &xe2) < 0) { + xdl_free_env(&xe1); return -1; } if (xdl_change_compact(&xe1.xdf1, &xe1.xdf2, xpp->flags) < 0 || @@ -592,6 +657,8 @@ int xdl_merge(mmfile_t *orig, mmfile_t *mf1, mmfile_t *mf2, if (xdl_change_compact(&xe2.xdf1, &xe2.xdf2, xpp->flags) < 0 || xdl_change_compact(&xe2.xdf2, &xe2.xdf1, xpp->flags) < 0 || xdl_build_script(&xe2, &xscr2) < 0) { + xdl_free_script(xscr1); + xdl_free_env(&xe1); xdl_free_env(&xe2); return -1; } diff --git a/xdiff/xpatience.c b/xdiff/xpatience.c index e42c16a807..9f91702de7 100644 --- a/xdiff/xpatience.c +++ b/xdiff/xpatience.c @@ -1,6 +1,6 @@ /* * LibXDiff by Davide Libenzi ( File Differential Library ) - * Copyright (C) 2003-2009 Davide Libenzi, Johannes E. Schindelin + * Copyright (C) 2003-2016 Davide Libenzi, Johannes E. Schindelin * * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public @@ -166,7 +166,7 @@ static int binary_search(struct entry **sequence, int longest, int left = -1, right = longest; while (left + 1 < right) { - int middle = (left + right) / 2; + int middle = left + (right - left) / 2; /* by construction, no two entries can be equal */ if (sequence[middle]->line2 > entry->line2) right = middle; @@ -287,34 +287,11 @@ static int walk_common_sequence(struct hashmap *map, struct entry *first, static int fall_back_to_classic_diff(struct hashmap *map, int line1, int count1, int line2, int count2) { - /* - * This probably does not work outside Git, since - * we have a very simple mmfile structure. - * - * Note: ideally, we would reuse the prepared environment, but - * the libxdiff interface does not (yet) allow for diffing only - * ranges of lines instead of the whole files. - */ - mmfile_t subfile1, subfile2; xpparam_t xpp; - xdfenv_t env; - - subfile1.ptr = (char *)map->env->xdf1.recs[line1 - 1]->ptr; - subfile1.size = map->env->xdf1.recs[line1 + count1 - 2]->ptr + - map->env->xdf1.recs[line1 + count1 - 2]->size - subfile1.ptr; - subfile2.ptr = (char *)map->env->xdf2.recs[line2 - 1]->ptr; - subfile2.size = map->env->xdf2.recs[line2 + count2 - 2]->ptr + - map->env->xdf2.recs[line2 + count2 - 2]->size - subfile2.ptr; - xpp.flags = map->xpp->flags & ~XDF_PATIENCE_DIFF; - if (xdl_do_diff(&subfile1, &subfile2, &xpp, &env) < 0) - return -1; + xpp.flags = map->xpp->flags & ~XDF_DIFF_ALGORITHM_MASK; - memcpy(map->env->xdf1.rchg + line1 - 1, env.xdf1.rchg, count1); - memcpy(map->env->xdf2.rchg + line2 - 1, env.xdf2.rchg, count2); - - xdl_free_env(&env); - - return 0; + return xdl_fall_back_diff(map->env, &xpp, + line1, count1, line2, count2); } /* diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c index 1689085235..13b55aba74 100644 --- a/xdiff/xprepare.c +++ b/xdiff/xprepare.c @@ -26,6 +26,8 @@ #define XDL_KPDIS_RUN 4 #define XDL_MAX_EQLIMIT 1024 #define XDL_SIMSCAN_WINDOW 100 +#define XDL_GUESS_NLINES1 256 +#define XDL_GUESS_NLINES2 20 typedef struct s_xdlclass { @@ -34,6 +36,7 @@ typedef struct s_xdlclass { char const *line; long size; long idx; + long len1, len2; } xdlclass_t; typedef struct s_xdlclassifier { @@ -41,6 +44,8 @@ typedef struct s_xdlclassifier { long hsize; xdlclass_t **rchash; chastore_t ncha; + xdlclass_t **rcrecs; + long alloc; long count; long flags; } xdlclassifier_t; @@ -50,22 +55,20 @@ typedef struct s_xdlclassifier { static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags); static void xdl_free_classifier(xdlclassifier_t *cf); -static int xdl_classify_record(xdlclassifier_t *cf, xrecord_t **rhash, unsigned int hbits, - xrecord_t *rec); -static int xdl_prepare_ctx(mmfile_t *mf, long narec, xpparam_t const *xpp, +static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t **rhash, + unsigned int hbits, xrecord_t *rec); +static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp, xdlclassifier_t *cf, xdfile_t *xdf); static void xdl_free_ctx(xdfile_t *xdf); static int xdl_clean_mmatch(char const *dis, long i, long s, long e); -static int xdl_cleanup_records(xdfile_t *xdf1, xdfile_t *xdf2); +static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2); static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2); -static int xdl_optimize_ctxs(xdfile_t *xdf1, xdfile_t *xdf2); +static int xdl_optimize_ctxs(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2); static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags) { - long i; - cf->flags = flags; cf->hbits = xdl_hashbits((unsigned int) size); @@ -80,8 +83,15 @@ static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags) { xdl_cha_free(&cf->ncha); return -1; } - for (i = 0; i < cf->hsize; i++) - cf->rchash[i] = NULL; + memset(cf->rchash, 0, cf->hsize * sizeof(xdlclass_t *)); + + cf->alloc = size; + if (!(cf->rcrecs = (xdlclass_t **) xdl_malloc(cf->alloc * sizeof(xdlclass_t *)))) { + + xdl_free(cf->rchash); + xdl_cha_free(&cf->ncha); + return -1; + } cf->count = 0; @@ -91,16 +101,18 @@ static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags) { static void xdl_free_classifier(xdlclassifier_t *cf) { + xdl_free(cf->rcrecs); xdl_free(cf->rchash); xdl_cha_free(&cf->ncha); } -static int xdl_classify_record(xdlclassifier_t *cf, xrecord_t **rhash, unsigned int hbits, - xrecord_t *rec) { +static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t **rhash, + unsigned int hbits, xrecord_t *rec) { long hi; char const *line; xdlclass_t *rcrec; + xdlclass_t **rcrecs; line = rec->ptr; hi = (long) XDL_HASHLONG(rec->ha, cf->hbits); @@ -116,13 +128,25 @@ static int xdl_classify_record(xdlclassifier_t *cf, xrecord_t **rhash, unsigned return -1; } rcrec->idx = cf->count++; + if (cf->count > cf->alloc) { + cf->alloc *= 2; + if (!(rcrecs = (xdlclass_t **) xdl_realloc(cf->rcrecs, cf->alloc * sizeof(xdlclass_t *)))) { + + return -1; + } + cf->rcrecs = rcrecs; + } + cf->rcrecs[rcrec->idx] = rcrec; rcrec->line = line; rcrec->size = rec->size; rcrec->ha = rec->ha; + rcrec->len1 = rcrec->len2 = 0; rcrec->next = cf->rchash[hi]; cf->rchash[hi] = rcrec; } + (pass == 1) ? rcrec->len1++ : rcrec->len2++; + rec->ha = (unsigned long) rcrec->idx; hi = (long) XDL_HASHLONG(rec->ha, hbits); @@ -133,10 +157,10 @@ static int xdl_classify_record(xdlclassifier_t *cf, xrecord_t **rhash, unsigned } -static int xdl_prepare_ctx(mmfile_t *mf, long narec, xpparam_t const *xpp, +static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp, xdlclassifier_t *cf, xdfile_t *xdf) { unsigned int hbits; - long i, nrec, hsize, bsize; + long nrec, hsize, bsize; unsigned long hav; char const *blk, *cur, *top, *prev; xrecord_t *crec; @@ -146,96 +170,59 @@ static int xdl_prepare_ctx(mmfile_t *mf, long narec, xpparam_t const *xpp, char *rchg; long *rindex; - if (xdl_cha_init(&xdf->rcha, sizeof(xrecord_t), narec / 4 + 1) < 0) { - - return -1; + ha = NULL; + rindex = NULL; + rchg = NULL; + rhash = NULL; + recs = NULL; + + if (xdl_cha_init(&xdf->rcha, sizeof(xrecord_t), narec / 4 + 1) < 0) + goto abort; + if (!(recs = (xrecord_t **) xdl_malloc(narec * sizeof(xrecord_t *)))) + goto abort; + + if (XDF_DIFF_ALG(xpp->flags) == XDF_HISTOGRAM_DIFF) + hbits = hsize = 0; + else { + hbits = xdl_hashbits((unsigned int) narec); + hsize = 1 << hbits; + if (!(rhash = (xrecord_t **) xdl_malloc(hsize * sizeof(xrecord_t *)))) + goto abort; + memset(rhash, 0, hsize * sizeof(xrecord_t *)); } - if (!(recs = (xrecord_t **) xdl_malloc(narec * sizeof(xrecord_t *)))) { - - xdl_cha_free(&xdf->rcha); - return -1; - } - - hbits = xdl_hashbits((unsigned int) narec); - hsize = 1 << hbits; - if (!(rhash = (xrecord_t **) xdl_malloc(hsize * sizeof(xrecord_t *)))) { - - xdl_free(recs); - xdl_cha_free(&xdf->rcha); - return -1; - } - for (i = 0; i < hsize; i++) - rhash[i] = NULL; nrec = 0; if ((cur = blk = xdl_mmfile_first(mf, &bsize)) != NULL) { - for (top = blk + bsize;;) { - if (cur >= top) { - if (!(cur = blk = xdl_mmfile_next(mf, &bsize))) - break; - top = blk + bsize; - } + for (top = blk + bsize; cur < top; ) { prev = cur; hav = xdl_hash_record(&cur, top, xpp->flags); if (nrec >= narec) { narec *= 2; - if (!(rrecs = (xrecord_t **) xdl_realloc(recs, narec * sizeof(xrecord_t *)))) { - - xdl_free(rhash); - xdl_free(recs); - xdl_cha_free(&xdf->rcha); - return -1; - } + if (!(rrecs = (xrecord_t **) xdl_realloc(recs, narec * sizeof(xrecord_t *)))) + goto abort; recs = rrecs; } - if (!(crec = xdl_cha_alloc(&xdf->rcha))) { - - xdl_free(rhash); - xdl_free(recs); - xdl_cha_free(&xdf->rcha); - return -1; - } + if (!(crec = xdl_cha_alloc(&xdf->rcha))) + goto abort; crec->ptr = prev; crec->size = (long) (cur - prev); crec->ha = hav; recs[nrec++] = crec; - if (xdl_classify_record(cf, rhash, hbits, crec) < 0) { - - xdl_free(rhash); - xdl_free(recs); - xdl_cha_free(&xdf->rcha); - return -1; - } + if ((XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF) && + xdl_classify_record(pass, cf, rhash, hbits, crec) < 0) + goto abort; } } - if (!(rchg = (char *) xdl_malloc((nrec + 2) * sizeof(char)))) { - - xdl_free(rhash); - xdl_free(recs); - xdl_cha_free(&xdf->rcha); - return -1; - } + if (!(rchg = (char *) xdl_malloc((nrec + 2) * sizeof(char)))) + goto abort; memset(rchg, 0, (nrec + 2) * sizeof(char)); - if (!(rindex = (long *) xdl_malloc((nrec + 1) * sizeof(long)))) { - - xdl_free(rchg); - xdl_free(rhash); - xdl_free(recs); - xdl_cha_free(&xdf->rcha); - return -1; - } - if (!(ha = (unsigned long *) xdl_malloc((nrec + 1) * sizeof(unsigned long)))) { - - xdl_free(rindex); - xdl_free(rchg); - xdl_free(rhash); - xdl_free(recs); - xdl_cha_free(&xdf->rcha); - return -1; - } + if (!(rindex = (long *) xdl_malloc((nrec + 1) * sizeof(long)))) + goto abort; + if (!(ha = (unsigned long *) xdl_malloc((nrec + 1) * sizeof(unsigned long)))) + goto abort; xdf->nrec = nrec; xdf->recs = recs; @@ -249,6 +236,15 @@ static int xdl_prepare_ctx(mmfile_t *mf, long narec, xpparam_t const *xpp, xdf->dend = nrec - 1; return 0; + +abort: + xdl_free(ha); + xdl_free(rindex); + xdl_free(rchg); + xdl_free(rhash); + xdl_free(recs); + xdl_cha_free(&xdf->rcha); + return -1; } @@ -265,39 +261,53 @@ static void xdl_free_ctx(xdfile_t *xdf) { int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, xdfenv_t *xe) { - long enl1, enl2; + long enl1, enl2, sample; xdlclassifier_t cf; - enl1 = xdl_guess_lines(mf1) + 1; - enl2 = xdl_guess_lines(mf2) + 1; + memset(&cf, 0, sizeof(cf)); + + /* + * For histogram diff, we can afford a smaller sample size and + * thus a poorer estimate of the number of lines, as the hash + * table (rhash) won't be filled up/grown. The number of lines + * (nrecs) will be updated correctly anyway by + * xdl_prepare_ctx(). + */ + sample = (XDF_DIFF_ALG(xpp->flags) == XDF_HISTOGRAM_DIFF + ? XDL_GUESS_NLINES2 : XDL_GUESS_NLINES1); - if (xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0) { + enl1 = xdl_guess_lines(mf1, sample) + 1; + enl2 = xdl_guess_lines(mf2, sample) + 1; + if (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF && + xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0) return -1; - } - if (xdl_prepare_ctx(mf1, enl1, xpp, &cf, &xe->xdf1) < 0) { + if (xdl_prepare_ctx(1, mf1, enl1, xpp, &cf, &xe->xdf1) < 0) { xdl_free_classifier(&cf); return -1; } - if (xdl_prepare_ctx(mf2, enl2, xpp, &cf, &xe->xdf2) < 0) { + if (xdl_prepare_ctx(2, mf2, enl2, xpp, &cf, &xe->xdf2) < 0) { xdl_free_ctx(&xe->xdf1); xdl_free_classifier(&cf); return -1; } - xdl_free_classifier(&cf); - - if (!(xpp->flags & XDF_PATIENCE_DIFF) && - xdl_optimize_ctxs(&xe->xdf1, &xe->xdf2) < 0) { + if ((XDF_DIFF_ALG(xpp->flags) != XDF_PATIENCE_DIFF) && + (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF) && + xdl_optimize_ctxs(&cf, &xe->xdf1, &xe->xdf2) < 0) { xdl_free_ctx(&xe->xdf2); xdl_free_ctx(&xe->xdf1); + xdl_free_classifier(&cf); return -1; } + if (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF) + xdl_free_classifier(&cf); + return 0; } @@ -372,11 +382,10 @@ static int xdl_clean_mmatch(char const *dis, long i, long s, long e) { * matches on the other file. Also, lines that have multiple matches * might be potentially discarded if they happear in a run of discardable. */ -static int xdl_cleanup_records(xdfile_t *xdf1, xdfile_t *xdf2) { - long i, nm, rhi, nreff, mlim; - unsigned long hav; +static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) { + long i, nm, nreff, mlim; xrecord_t **recs; - xrecord_t *rec; + xdlclass_t *rcrec; char *dis, *dis1, *dis2; if (!(dis = (char *) xdl_malloc(xdf1->nrec + xdf2->nrec + 2))) { @@ -390,22 +399,16 @@ static int xdl_cleanup_records(xdfile_t *xdf1, xdfile_t *xdf2) { if ((mlim = xdl_bogosqrt(xdf1->nrec)) > XDL_MAX_EQLIMIT) mlim = XDL_MAX_EQLIMIT; for (i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart]; i <= xdf1->dend; i++, recs++) { - hav = (*recs)->ha; - rhi = (long) XDL_HASHLONG(hav, xdf2->hbits); - for (nm = 0, rec = xdf2->rhash[rhi]; rec; rec = rec->next) - if (rec->ha == hav && ++nm == mlim) - break; + rcrec = cf->rcrecs[(*recs)->ha]; + nm = rcrec ? rcrec->len2 : 0; dis1[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1; } if ((mlim = xdl_bogosqrt(xdf2->nrec)) > XDL_MAX_EQLIMIT) mlim = XDL_MAX_EQLIMIT; for (i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart]; i <= xdf2->dend; i++, recs++) { - hav = (*recs)->ha; - rhi = (long) XDL_HASHLONG(hav, xdf1->hbits); - for (nm = 0, rec = xdf1->rhash[rhi]; rec; rec = rec->next) - if (rec->ha == hav && ++nm == mlim) - break; + rcrec = cf->rcrecs[(*recs)->ha]; + nm = rcrec ? rcrec->len1 : 0; dis2[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1; } @@ -468,10 +471,10 @@ static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2) { } -static int xdl_optimize_ctxs(xdfile_t *xdf1, xdfile_t *xdf2) { +static int xdl_optimize_ctxs(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) { if (xdl_trim_ends(xdf1, xdf2) < 0 || - xdl_cleanup_records(xdf1, xdf2) < 0) { + xdl_cleanup_records(cf, xdf1, xdf2) < 0) { return -1; } diff --git a/xdiff/xutils.c b/xdiff/xutils.c index ab6503460f..04d7b32e4e 100644 --- a/xdiff/xutils.c +++ b/xdiff/xutils.c @@ -20,14 +20,12 @@ * */ +#include <limits.h> +#include <assert.h> #include "xinclude.h" -#define XDL_GUESS_NLINES 256 - - - long xdl_bogosqrt(long n) { long i; @@ -71,12 +69,6 @@ void *xdl_mmfile_first(mmfile_t *mmf, long *size) } -void *xdl_mmfile_next(mmfile_t *mmf, long *size) -{ - return NULL; -} - - long xdl_mmfile_size(mmfile_t *mmf) { return mmf->size; @@ -130,47 +122,12 @@ void *xdl_cha_alloc(chastore_t *cha) { return data; } - -void *xdl_cha_first(chastore_t *cha) { - chanode_t *sncur; - - if (!(cha->sncur = sncur = cha->head)) - return NULL; - - cha->scurr = 0; - - return (char *) sncur + sizeof(chanode_t) + cha->scurr; -} - - -void *xdl_cha_next(chastore_t *cha) { - chanode_t *sncur; - - if (!(sncur = cha->sncur)) - return NULL; - cha->scurr += cha->isize; - if (cha->scurr == sncur->icurr) { - if (!(sncur = cha->sncur = sncur->next)) - return NULL; - cha->scurr = 0; - } - - return (char *) sncur + sizeof(chanode_t) + cha->scurr; -} - - -long xdl_guess_lines(mmfile_t *mf) { +long xdl_guess_lines(mmfile_t *mf, long sample) { long nl = 0, size, tsize = 0; char const *data, *cur, *top; if ((cur = data = xdl_mmfile_first(mf, &size)) != NULL) { - for (top = data + size; nl < XDL_GUESS_NLINES;) { - if (cur >= top) { - tsize += (long) (cur - data); - if (!(cur = data = xdl_mmfile_next(mf, &size))) - break; - top = data + size; - } + for (top = data + size; nl < sample && cur < top; ) { nl++; if (!(cur = memchr(cur, '\n', top - cur))) cur = top; @@ -186,6 +143,19 @@ long xdl_guess_lines(mmfile_t *mf) { return nl + 1; } +int xdl_blankline(const char *line, long size, long flags) +{ + long i; + + if (!(flags & XDF_WHITESPACE_FLAGS)) + return (size <= 1); + + for (i = 0; i < size && XDL_ISSPACE(line[i]); i++) + ; + + return (i == size); +} + int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags) { int i1, i2; @@ -230,8 +200,10 @@ int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags) return 0; } } else if (flags & XDF_IGNORE_WHITESPACE_AT_EOL) { - while (i1 < s1 && i2 < s2 && l1[i1++] == l2[i2++]) - ; /* keep going */ + while (i1 < s1 && i2 < s2 && l1[i1] == l2[i2]) { + i1++; + i2++; + } } /* @@ -292,7 +264,6 @@ static unsigned long xdl_hash_record_with_whitespace(char const **data, return ha; } - unsigned long xdl_hash_record(char const **data, char const *top, long flags) { unsigned long ha = 5381; char const *ptr = *data; @@ -309,7 +280,6 @@ unsigned long xdl_hash_record(char const **data, char const *top, long flags) { return ha; } - unsigned int xdl_hashbits(unsigned int size) { unsigned int val = 1, bits = 0; @@ -340,20 +310,6 @@ int xdl_num_out(char *out, long val) { return str - out; } - -long xdl_atol(char const *str, char const **next) { - long val, base; - char const *top; - - for (top = str; XDL_ISDIGIT(*top); top++); - if (next) - *next = top; - for (val = 0, base = 1, top--; top >= str; top--, base *= 10) - val += base * (long)(*top - '0'); - return val; -} - - int xdl_emit_hunk_hdr(long s1, long c1, long s2, long c2, const char *func, long funclen, xdemitcb_t *ecb) { int nb = 0; @@ -402,3 +358,34 @@ int xdl_emit_hunk_hdr(long s1, long c1, long s2, long c2, return 0; } + +int xdl_fall_back_diff(xdfenv_t *diff_env, xpparam_t const *xpp, + int line1, int count1, int line2, int count2) +{ + /* + * This probably does not work outside Git, since + * we have a very simple mmfile structure. + * + * Note: ideally, we would reuse the prepared environment, but + * the libxdiff interface does not (yet) allow for diffing only + * ranges of lines instead of the whole files. + */ + mmfile_t subfile1, subfile2; + xdfenv_t env; + + subfile1.ptr = (char *)diff_env->xdf1.recs[line1 - 1]->ptr; + subfile1.size = diff_env->xdf1.recs[line1 + count1 - 2]->ptr + + diff_env->xdf1.recs[line1 + count1 - 2]->size - subfile1.ptr; + subfile2.ptr = (char *)diff_env->xdf2.recs[line2 - 1]->ptr; + subfile2.size = diff_env->xdf2.recs[line2 + count2 - 2]->ptr + + diff_env->xdf2.recs[line2 + count2 - 2]->size - subfile2.ptr; + if (xdl_do_diff(&subfile1, &subfile2, xpp, &env) < 0) + return -1; + + memcpy(diff_env->xdf1.rchg + line1 - 1, env.xdf1.rchg, count1); + memcpy(diff_env->xdf2.rchg + line2 - 1, env.xdf2.rchg, count2); + + xdl_free_env(&env); + + return 0; +} diff --git a/xdiff/xutils.h b/xdiff/xutils.h index d5de8292e0..4646ce5752 100644 --- a/xdiff/xutils.h +++ b/xdiff/xutils.h @@ -31,16 +31,16 @@ int xdl_emit_diffrec(char const *rec, long size, char const *pre, long psize, int xdl_cha_init(chastore_t *cha, long isize, long icount); void xdl_cha_free(chastore_t *cha); void *xdl_cha_alloc(chastore_t *cha); -void *xdl_cha_first(chastore_t *cha); -void *xdl_cha_next(chastore_t *cha); -long xdl_guess_lines(mmfile_t *mf); +long xdl_guess_lines(mmfile_t *mf, long sample); +int xdl_blankline(const char *line, long size, long flags); int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags); unsigned long xdl_hash_record(char const **data, char const *top, long flags); unsigned int xdl_hashbits(unsigned int size); int xdl_num_out(char *out, long val); -long xdl_atol(char const *str, char const **next); int xdl_emit_hunk_hdr(long s1, long c1, long s2, long c2, const char *func, long funclen, xdemitcb_t *ecb); +int xdl_fall_back_diff(xdfenv_t *diff_env, xpparam_t const *xpp, + int line1, int count1, int line2, int count2); |