diff options
Diffstat (limited to 'xdiff')
| -rw-r--r-- | xdiff/xdiff.h | 146 | ||||
| -rw-r--r-- | xdiff/xdiffi.c | 1043 | ||||
| -rw-r--r-- | xdiff/xdiffi.h | 64 | ||||
| -rw-r--r-- | xdiff/xemit.c | 312 | ||||
| -rw-r--r-- | xdiff/xemit.h | 36 | ||||
| -rw-r--r-- | xdiff/xhistogram.c | 384 | ||||
| -rw-r--r-- | xdiff/xinclude.h | 36 | ||||
| -rw-r--r-- | xdiff/xmacros.h | 54 | ||||
| -rw-r--r-- | xdiff/xmerge.c | 686 | ||||
| -rw-r--r-- | xdiff/xpatience.c | 388 | ||||
| -rw-r--r-- | xdiff/xprepare.c | 483 | ||||
| -rw-r--r-- | xdiff/xprepare.h | 34 | ||||
| -rw-r--r-- | xdiff/xtypes.h | 67 | ||||
| -rw-r--r-- | xdiff/xutils.c | 434 | ||||
| -rw-r--r-- | xdiff/xutils.h | 47 |
15 files changed, 4214 insertions, 0 deletions
diff --git a/xdiff/xdiff.h b/xdiff/xdiff.h new file mode 100644 index 000000000000..032e3a9f41a2 --- /dev/null +++ b/xdiff/xdiff.h @@ -0,0 +1,146 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/>. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XDIFF_H) +#define XDIFF_H + +#ifdef __cplusplus +extern "C" { +#endif /* #ifdef __cplusplus */ + +/* xpparm_t.flags */ +#define XDF_NEED_MINIMAL (1 << 0) + +#define XDF_IGNORE_WHITESPACE (1 << 1) +#define XDF_IGNORE_WHITESPACE_CHANGE (1 << 2) +#define XDF_IGNORE_WHITESPACE_AT_EOL (1 << 3) +#define XDF_IGNORE_CR_AT_EOL (1 << 4) +#define XDF_WHITESPACE_FLAGS (XDF_IGNORE_WHITESPACE | \ + XDF_IGNORE_WHITESPACE_CHANGE | \ + XDF_IGNORE_WHITESPACE_AT_EOL | \ + XDF_IGNORE_CR_AT_EOL) + +#define XDF_IGNORE_BLANK_LINES (1 << 7) + +#define XDF_PATIENCE_DIFF (1 << 14) +#define XDF_HISTOGRAM_DIFF (1 << 15) +#define XDF_DIFF_ALGORITHM_MASK (XDF_PATIENCE_DIFF | XDF_HISTOGRAM_DIFF) +#define XDF_DIFF_ALG(x) ((x) & XDF_DIFF_ALGORITHM_MASK) + +#define XDF_INDENT_HEURISTIC (1 << 23) + +/* xdemitconf_t.flags */ +#define XDL_EMIT_FUNCNAMES (1 << 0) +#define XDL_EMIT_FUNCCONTEXT (1 << 2) + +/* merge simplification levels */ +#define XDL_MERGE_MINIMAL 0 +#define XDL_MERGE_EAGER 1 +#define XDL_MERGE_ZEALOUS 2 +#define XDL_MERGE_ZEALOUS_ALNUM 3 + +/* merge favor modes */ +#define XDL_MERGE_FAVOR_OURS 1 +#define XDL_MERGE_FAVOR_THEIRS 2 +#define XDL_MERGE_FAVOR_UNION 3 + +/* merge output styles */ +#define XDL_MERGE_DIFF3 1 + +typedef struct s_mmfile { + char *ptr; + long size; +} mmfile_t; + +typedef struct s_mmbuffer { + char *ptr; + long size; +} mmbuffer_t; + +typedef struct s_xpparam { + unsigned long flags; + + /* See Documentation/diff-options.txt. */ + char **anchors; + size_t anchors_nr; +} xpparam_t; + +typedef struct s_xdemitcb { + void *priv; + int (*out_hunk)(void *, + long old_begin, long old_nr, + long new_begin, long new_nr, + const char *func, long funclen); + int (*out_line)(void *, mmbuffer_t *, int); +} xdemitcb_t; + +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; + xdl_emit_hunk_consume_func_t hunk_func; +} xdemitconf_t; + +typedef struct s_bdiffparam { + long bsize; +} bdiffparam_t; + + +#define xdl_malloc(x) xmalloc(x) +#define xdl_free(ptr) free(ptr) +#define xdl_realloc(ptr,x) xrealloc(ptr,x) + +void *xdl_mmfile_first(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, + xdemitconf_t const *xecfg, xdemitcb_t *ecb); + +typedef struct s_xmparam { + xpparam_t xpp; + int marker_size; + int level; + int favor; + int style; + const char *ancestor; /* label for orig */ + const char *file1; /* label for mf1 */ + const char *file2; /* label for mf2 */ +} xmparam_t; + +#define DEFAULT_CONFLICT_MARKER_SIZE 7 + +int xdl_merge(mmfile_t *orig, mmfile_t *mf1, mmfile_t *mf2, + xmparam_t const *xmp, mmbuffer_t *result); + +#ifdef __cplusplus +} +#endif /* #ifdef __cplusplus */ + +#endif /* #if !defined(XDIFF_H) */ diff --git a/xdiff/xdiffi.c b/xdiff/xdiffi.c new file mode 100644 index 000000000000..1f1f4a3c7808 --- /dev/null +++ b/xdiff/xdiffi.c @@ -0,0 +1,1043 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/>. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#include "xinclude.h" + +#define XDL_MAX_COST_MIN 256 +#define XDL_HEUR_MIN_COST 256 +#define XDL_LINE_MAX (long)((1UL << (CHAR_BIT * sizeof(long) - 1)) - 1) +#define XDL_SNAKE_CNT 20 +#define XDL_K_HEUR 4 + +typedef struct s_xdpsplit { + long i1, i2; + int min_lo, min_hi; +} xdpsplit_t; + +/* + * See "An O(ND) Difference Algorithm and its Variations", by Eugene Myers. + * 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. + */ +static long xdl_split(unsigned long const *ha1, long off1, long lim1, + unsigned long const *ha2, long off2, long lim2, + long *kvdf, long *kvdb, int need_min, xdpsplit_t *spl, + xdalgoenv_t *xenv) { + long dmin = off1 - lim2, dmax = lim1 - off2; + long fmid = off1 - off2, bmid = lim1 - lim2; + long odd = (fmid - bmid) & 1; + long fmin = fmid, fmax = fmid; + long bmin = bmid, bmax = bmid; + long ec, d, i1, i2, prev1, best, dd, v, k; + + /* + * Set initial diagonal values for both forward and backward path. + */ + kvdf[fmid] = off1; + kvdb[bmid] = lim1; + + for (ec = 1;; ec++) { + int got_snake = 0; + + /* + * We need to extent 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. + * Also we initialize the external K value to -1 so that we can + * avoid extra conditions check inside the core loop. + */ + if (fmin > dmin) + kvdf[--fmin - 1] = -1; + else + ++fmin; + if (fmax < dmax) + kvdf[++fmax + 1] = -1; + else + --fmax; + + for (d = fmax; d >= fmin; d -= 2) { + if (kvdf[d - 1] >= kvdf[d + 1]) + i1 = kvdf[d - 1] + 1; + else + i1 = kvdf[d + 1]; + prev1 = i1; + i2 = i1 - d; + for (; i1 < lim1 && i2 < lim2 && ha1[i1] == ha2[i2]; i1++, i2++); + if (i1 - prev1 > xenv->snake_cnt) + got_snake = 1; + kvdf[d] = i1; + if (odd && bmin <= d && d <= bmax && kvdb[d] <= i1) { + spl->i1 = i1; + spl->i2 = i2; + spl->min_lo = spl->min_hi = 1; + return ec; + } + } + + /* + * We need to extent 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. + * Also we initialize the external K value to -1 so that we can + * avoid extra conditions check inside the core loop. + */ + if (bmin > dmin) + kvdb[--bmin - 1] = XDL_LINE_MAX; + else + ++bmin; + if (bmax < dmax) + kvdb[++bmax + 1] = XDL_LINE_MAX; + else + --bmax; + + for (d = bmax; d >= bmin; d -= 2) { + if (kvdb[d - 1] < kvdb[d + 1]) + i1 = kvdb[d - 1]; + else + i1 = kvdb[d + 1] - 1; + prev1 = i1; + i2 = i1 - d; + for (; i1 > off1 && i2 > off2 && ha1[i1 - 1] == ha2[i2 - 1]; i1--, i2--); + if (prev1 - i1 > xenv->snake_cnt) + got_snake = 1; + kvdb[d] = i1; + if (!odd && fmin <= d && d <= fmax && i1 <= kvdf[d]) { + spl->i1 = i1; + spl->i2 = i2; + spl->min_lo = spl->min_hi = 1; + return ec; + } + } + + if (need_min) + continue; + + /* + * 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 + * 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 + * edit cost times a magic factor (XDL_K_HEUR) we consider + * it interesting. + */ + if (got_snake && ec > xenv->heur_min) { + for (best = 0, d = fmax; d >= fmin; d -= 2) { + dd = d > fmid ? d - fmid: fmid - d; + i1 = kvdf[d]; + i2 = i1 - d; + v = (i1 - off1) + (i2 - off2) - dd; + + if (v > XDL_K_HEUR * ec && v > best && + off1 + xenv->snake_cnt <= i1 && i1 < lim1 && + off2 + xenv->snake_cnt <= i2 && i2 < lim2) { + for (k = 1; ha1[i1 - k] == ha2[i2 - k]; k++) + if (k == xenv->snake_cnt) { + best = v; + spl->i1 = i1; + spl->i2 = i2; + break; + } + } + } + if (best > 0) { + spl->min_lo = 1; + spl->min_hi = 0; + return ec; + } + + for (best = 0, d = bmax; d >= bmin; d -= 2) { + dd = d > bmid ? d - bmid: bmid - d; + i1 = kvdb[d]; + i2 = i1 - d; + v = (lim1 - i1) + (lim2 - i2) - dd; + + if (v > XDL_K_HEUR * ec && v > best && + off1 < i1 && i1 <= lim1 - xenv->snake_cnt && + off2 < i2 && i2 <= lim2 - xenv->snake_cnt) { + for (k = 0; ha1[i1 + k] == ha2[i2 + k]; k++) + if (k == xenv->snake_cnt - 1) { + best = v; + spl->i1 = i1; + spl->i2 = i2; + break; + } + } + } + if (best > 0) { + spl->min_lo = 0; + spl->min_hi = 1; + return ec; + } + } + + /* + * 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; + + fbest = fbest1 = -1; + for (d = fmax; d >= fmin; d -= 2) { + i1 = XDL_MIN(kvdf[d], lim1); + i2 = i1 - d; + if (lim2 < i2) + i1 = lim2 + d, i2 = lim2; + if (fbest < i1 + i2) { + fbest = i1 + i2; + fbest1 = i1; + } + } + + bbest = bbest1 = XDL_LINE_MAX; + for (d = bmax; d >= bmin; d -= 2) { + i1 = XDL_MAX(off1, kvdb[d]); + i2 = i1 - d; + if (i2 < off2) + i1 = off2 + d, i2 = off2; + if (i1 + i2 < bbest) { + bbest = i1 + i2; + bbest1 = i1; + } + } + + if ((lim1 + lim2) - bbest < fbest - (off1 + off2)) { + spl->i1 = fbest1; + spl->i2 = fbest - fbest1; + spl->min_lo = 1; + spl->min_hi = 0; + } else { + spl->i1 = bbest1; + spl->i2 = bbest - bbest1; + spl->min_lo = 0; + spl->min_hi = 1; + } + return ec; + } + } +} + + +/* + * 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. + */ +int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1, + diffdata_t *dd2, long off2, long lim2, + long *kvdf, long *kvdb, int need_min, xdalgoenv_t *xenv) { + unsigned long const *ha1 = dd1->ha, *ha2 = dd2->ha; + + /* + * Shrink the box by walking through each diagonal snake (SW and NE). + */ + for (; off1 < lim1 && off2 < lim2 && ha1[off1] == ha2[off2]; off1++, off2++); + for (; off1 < lim1 && off2 < lim2 && ha1[lim1 - 1] == ha2[lim2 - 1]; lim1--, lim2--); + + /* + * If one dimension is empty, then all records on the other one must + * be obviously changed. + */ + if (off1 == lim1) { + char *rchg2 = dd2->rchg; + long *rindex2 = dd2->rindex; + + for (; off2 < lim2; off2++) + rchg2[rindex2[off2]] = 1; + } else if (off2 == lim2) { + char *rchg1 = dd1->rchg; + long *rindex1 = dd1->rindex; + + for (; off1 < lim1; off1++) + rchg1[rindex1[off1]] = 1; + } else { + xdpsplit_t spl; + spl.i1 = spl.i2 = 0; + + /* + * Divide ... + */ + if (xdl_split(ha1, off1, lim1, ha2, off2, lim2, kvdf, kvdb, + need_min, &spl, xenv) < 0) { + + return -1; + } + + /* + * ... et Impera. + */ + if (xdl_recs_cmp(dd1, off1, spl.i1, dd2, off2, spl.i2, + kvdf, kvdb, spl.min_lo, xenv) < 0 || + xdl_recs_cmp(dd1, spl.i1, lim1, dd2, spl.i2, lim2, + kvdf, kvdb, spl.min_hi, xenv) < 0) { + + return -1; + } + } + + return 0; +} + + +int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, + xdfenv_t *xe) { + long ndiags; + long *kvd, *kvdf, *kvdb; + xdalgoenv_t xenv; + diffdata_t dd1, dd2; + + 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; + } + + /* + * 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 (!(kvd = (long *) xdl_malloc((2 * ndiags + 2) * sizeof(long)))) { + + xdl_free_env(xe); + return -1; + } + kvdf = kvd; + kvdb = kvdf + ndiags; + kvdf += xe->xdf2.nreff + 1; + kvdb += xe->xdf2.nreff + 1; + + xenv.mxcost = xdl_bogosqrt(ndiags); + if (xenv.mxcost < XDL_MAX_COST_MIN) + xenv.mxcost = XDL_MAX_COST_MIN; + xenv.snake_cnt = XDL_SNAKE_CNT; + xenv.heur_min = XDL_HEUR_MIN_COST; + + dd1.nrec = xe->xdf1.nreff; + dd1.ha = xe->xdf1.ha; + dd1.rchg = xe->xdf1.rchg; + dd1.rindex = xe->xdf1.rindex; + dd2.nrec = xe->xdf2.nreff; + dd2.ha = xe->xdf2.ha; + dd2.rchg = xe->xdf2.rchg; + dd2.rindex = xe->xdf2.rindex; + + if (xdl_recs_cmp(&dd1, 0, dd1.nrec, &dd2, 0, dd2.nrec, + kvdf, kvdb, (xpp->flags & XDF_NEED_MINIMAL) != 0, &xenv) < 0) { + + xdl_free(kvd); + xdl_free_env(xe); + return -1; + } + + xdl_free(kvd); + + return 0; +} + + +static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1, long chg2) { + xdchange_t *xch; + + if (!(xch = (xdchange_t *) xdl_malloc(sizeof(xdchange_t)))) + return NULL; + + xch->next = xscr; + xch->i1 = i1; + xch->i2 = i2; + xch->chg1 = chg1; + xch->chg2 = chg2; + xch->ignore = 0; + + return xch; +} + + +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 { + /* + * Is the split at the end of the file (aside from any blank lines)? + */ + 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 + +/* + * How far do we slide a hunk at most? + */ +#define INDENT_HEURISTIC_MAX_SLIDING 100 + +/* + * 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 { + /* + * 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: + */ + 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 { + groupsize = g.end - g.start; + + /* + * 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: + */ + end_matching_other = -1; + + /* 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"); + + /* + * This is this highest that this group can be shifted. + * Record its end index: + */ + 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 (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. + */ + + 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; + + shift = earliest_end; + if (g.end - groupsize - 1 > shift) + shift = g.end - groupsize - 1; + if (g.end - INDENT_HEURISTIC_MAX_SLIDING > shift) + shift = g.end - INDENT_HEURISTIC_MAX_SLIDING; + for (; 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; +} + + +int xdl_build_script(xdfenv_t *xe, xdchange_t **xscr) { + xdchange_t *cscr = NULL, *xch; + char *rchg1 = xe->xdf1.rchg, *rchg2 = xe->xdf2.rchg; + long i1, i2, l1, l2; + + /* + * Trivial. Collects "groups" of changes and creates an edit script. + */ + for (i1 = xe->xdf1.nrec, i2 = xe->xdf2.nrec; i1 >= 0 || i2 >= 0; i1--, i2--) + if (rchg1[i1 - 1] || rchg2[i2 - 1]) { + for (l1 = i1; rchg1[i1 - 1]; i1--); + for (l2 = i2; rchg2[i2 - 1]; i2--); + + if (!(xch = xdl_add_change(cscr, i1, i2, l1 - i1, l2 - i2))) { + xdl_free_script(cscr); + return -1; + } + cscr = xch; + } + + *xscr = cscr; + + return 0; +} + + +void xdl_free_script(xdchange_t *xscr) { + xdchange_t *xch; + + while ((xch = xscr) != NULL) { + xscr = xscr->next; + xdl_free(xch); + } +} + +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->hunk_func ? xdl_call_hunk_func : xdl_emit_diff; + + if (xdl_do_diff(mf1, mf2, xpp, &xe) < 0) { + + return -1; + } + if (xdl_change_compact(&xe.xdf1, &xe.xdf2, xpp->flags) < 0 || + xdl_change_compact(&xe.xdf2, &xe.xdf1, xpp->flags) < 0 || + xdl_build_script(&xe, &xscr) < 0) { + + xdl_free_env(&xe); + 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); + xdl_free_env(&xe); + return -1; + } + xdl_free_script(xscr); + } + xdl_free_env(&xe); + + return 0; +} diff --git a/xdiff/xdiffi.h b/xdiff/xdiffi.h new file mode 100644 index 000000000000..8f1c7c8b0445 --- /dev/null +++ b/xdiff/xdiffi.h @@ -0,0 +1,64 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/>. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XDIFFI_H) +#define XDIFFI_H + + +typedef struct s_diffdata { + long nrec; + unsigned long const *ha; + long *rindex; + char *rchg; +} diffdata_t; + +typedef struct s_xdalgoenv { + long mxcost; + long snake_cnt; + long heur_min; +} xdalgoenv_t; + +typedef struct s_xdchange { + struct s_xdchange *next; + long i1, i2; + long chg1, chg2; + int ignore; +} xdchange_t; + + + +int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1, + diffdata_t *dd2, long off2, long lim2, + long *kvdf, long *kvdb, int need_min, xdalgoenv_t *xenv); +int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, + xdfenv_t *xe); +int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags); +int xdl_build_script(xdfenv_t *xe, xdchange_t **xscr); +void xdl_free_script(xdchange_t *xscr); +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 new file mode 100644 index 000000000000..30713ae9a98e --- /dev/null +++ b/xdiff/xemit.c @@ -0,0 +1,312 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/>. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#include "xinclude.h" + +static long xdl_get_rec(xdfile_t *xdf, long ri, char const **rec) { + + *rec = xdf->recs[ri]->ptr; + + return xdf->recs[ri]->size; +} + + +static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t *ecb) { + long size, psize = strlen(pre); + char const *rec; + + size = xdl_get_rec(xdf, ri, &rec); + if (xdl_emit_diffrec(rec, size, pre, psize, ecb) < 0) { + + return -1; + } + + return 0; +} + + +/* + * 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, *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 = xchp->next; xch; xchp = xch, xch = xch->next) { + long distance = xch->i1 - (xchp->i1 + xchp->chg1); + if (distance > max_common) + break; + + 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; +} + + +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 == '$')) { /* identifiers from VMS and other esoterico */ + if (len > sz) + len = sz; + while (0 < len && isspace((unsigned char)rec[len - 1])) + len--; + memcpy(buf, rec, len); + return len; + } + return -1; +} + +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); +} + +static int is_func_rec(xdfile_t *xdf, xdemitconf_t const *xecfg, long ri) +{ + char dummy[1]; + return match_func_rec(xdf, xecfg, ri, dummy, sizeof(dummy)) >= 0; +} + +struct func_line { + long len; + char buf[80]; +}; + +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 -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; + long funclineprev = -1; + struct func_line func_line = { 0 }; + + for (xch = xscr; xch; xch = xche->next) { + 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) { + long i2 = xch->i2; + + /* + * We don't need additional context if + * a whole function was added. + */ + while (i2 < xe->xdf2.nrec) { + if (is_func_rec(&xe->xdf2, xecfg, i2)) + 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); + while (fs1 > 0 && !is_empty_rec(&xe->xdf1, fs1 - 1) && + !is_func_rec(&xe->xdf1, xecfg, fs1 - 1)) + fs1--; + if (fs1 < 0) + fs1 = 0; + if (fs1 < s1) { + s2 = XDL_MAX(s2 - (s1 - fs1), 0); + 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)); + + 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 = XDL_MIN(e2 + (fe1 - e1), xe->xdf2.nrec); + 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) { + 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, + func_line.buf, func_line.len, ecb) < 0) + return -1; + + /* + * Emit pre-context. + */ + 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) { + /* + * Merge previous with current change atom. + */ + for (; s1 < xch->i1 && s2 < xch->i2; s1++, s2++) + if (xdl_emit_record(&xe->xdf2, s2, " ", ecb) < 0) + return -1; + + /* + * Removes lines from the first file. + */ + for (s1 = xch->i1; s1 < xch->i1 + xch->chg1; s1++) + if (xdl_emit_record(&xe->xdf1, s1, "-", ecb) < 0) + return -1; + + /* + * Adds lines from the second file. + */ + for (s2 = xch->i2; s2 < xch->i2 + xch->chg2; s2++) + if (xdl_emit_record(&xe->xdf2, s2, "+", ecb) < 0) + return -1; + + if (xch == xche) + break; + s1 = xch->i1 + xch->chg1; + s2 = xch->i2 + xch->chg2; + } + + /* + * Emit post-context. + */ + for (s2 = xche->i2 + xche->chg2; s2 < e2; s2++) + if (xdl_emit_record(&xe->xdf2, s2, " ", ecb) < 0) + return -1; + } + + return 0; +} diff --git a/xdiff/xemit.h b/xdiff/xemit.h new file mode 100644 index 000000000000..1b9887e670d4 --- /dev/null +++ b/xdiff/xemit.h @@ -0,0 +1,36 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/>. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XEMIT_H) +#define XEMIT_H + + +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); +int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, + xdemitconf_t const *xecfg); + + + +#endif /* #if !defined(XEMIT_H) */ diff --git a/xdiff/xhistogram.c b/xdiff/xhistogram.c new file mode 100644 index 000000000000..c7b35a9667f3 --- /dev/null +++ b/xdiff/xhistogram.c @@ -0,0 +1,384 @@ +/* + * 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" + +#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 fall_back_to_classic_diff(xpparam_t const *xpp, xdfenv_t *env, + int line1, int count1, int line2, int count2) +{ + xpparam_t xpparam; + xpparam.flags = xpp->flags & ~XDF_DIFF_ALGORITHM_MASK; + + return xdl_fall_back_diff(env, &xpparam, + line1, count1, line2, count2); +} + +static inline void free_index(struct histindex *index) +{ + xdl_free(index->records); + xdl_free(index->line_map); + xdl_free(index->next_ptrs); + xdl_cha_free(&index->rcha); +} + +static int find_lcs(xpparam_t const *xpp, xdfenv_t *env, + struct region *lcs, + int line1, int count1, int line2, int count2) +{ + int b_ptr; + int sz, ret = -1; + struct histindex index; + + 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; + + if (scanA(&index, line1, count1)) + goto cleanup; + + 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); + + if (index.has_common && index.max_chain_length < index.cnt) + ret = 1; + else + ret = 0; + +cleanup: + free_index(&index); + return ret; +} + +static int histogram_diff(xpparam_t const *xpp, xdfenv_t *env, + int line1, int count1, int line2, int count2) +{ + struct region lcs; + int lcs_found; + int result; +redo: + 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(&lcs, 0, sizeof(lcs)); + lcs_found = find_lcs(xpp, env, &lcs, line1, count1, line2, count2); + if (lcs_found < 0) + goto out; + else if (lcs_found) + result = fall_back_to_classic_diff(xpp, env, 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 out; + /* + * result = histogram_diff(xpp, env, + * lcs.end1 + 1, LINE_END(1) - lcs.end1, + * lcs.end2 + 1, LINE_END(2) - lcs.end2); + * but let's optimize tail recursion ourself: + */ + count1 = LINE_END(1) - lcs.end1; + line1 = lcs.end1 + 1; + count2 = LINE_END(2) - lcs.end2; + line2 = lcs.end2 + 1; + goto redo; + } + } +out: + 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/xinclude.h b/xdiff/xinclude.h new file mode 100644 index 000000000000..a4285ac0eb28 --- /dev/null +++ b/xdiff/xinclude.h @@ -0,0 +1,36 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/>. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XINCLUDE_H) +#define XINCLUDE_H + +#include "git-compat-util.h" +#include "xmacros.h" +#include "xdiff.h" +#include "xtypes.h" +#include "xutils.h" +#include "xprepare.h" +#include "xdiffi.h" +#include "xemit.h" + + +#endif /* #if !defined(XINCLUDE_H) */ diff --git a/xdiff/xmacros.h b/xdiff/xmacros.h new file mode 100644 index 000000000000..2809a28ca960 --- /dev/null +++ b/xdiff/xmacros.h @@ -0,0 +1,54 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/>. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XMACROS_H) +#define XMACROS_H + + + + +#define XDL_MIN(a, b) ((a) < (b) ? (a): (b)) +#define XDL_MAX(a, b) ((a) > (b) ? (a): (b)) +#define XDL_ABS(v) ((v) >= 0 ? (v): -(v)) +#define XDL_ISDIGIT(c) ((c) >= '0' && (c) <= '9') +#define XDL_ISSPACE(c) (isspace((unsigned char)(c))) +#define XDL_ADDBITS(v,b) ((v) + ((v) >> (b))) +#define XDL_MASKBITS(b) ((1UL << (b)) - 1) +#define XDL_HASHLONG(v,b) (XDL_ADDBITS((unsigned long)(v), b) & XDL_MASKBITS(b)) +#define XDL_PTRFREE(p) do { if (p) { xdl_free(p); (p) = NULL; } } while (0) +#define XDL_LE32_PUT(p, v) \ +do { \ + unsigned char *__p = (unsigned char *) (p); \ + *__p++ = (unsigned char) (v); \ + *__p++ = (unsigned char) ((v) >> 8); \ + *__p++ = (unsigned char) ((v) >> 16); \ + *__p = (unsigned char) ((v) >> 24); \ +} while (0) +#define XDL_LE32_GET(p, v) \ +do { \ + unsigned char const *__p = (unsigned char const *) (p); \ + (v) = (unsigned long) __p[0] | ((unsigned long) __p[1]) << 8 | \ + ((unsigned long) __p[2]) << 16 | ((unsigned long) __p[3]) << 24; \ +} while (0) + + +#endif /* #if !defined(XMACROS_H) */ diff --git a/xdiff/xmerge.c b/xdiff/xmerge.c new file mode 100644 index 000000000000..1659edb45393 --- /dev/null +++ b/xdiff/xmerge.c @@ -0,0 +1,686 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003-2006 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 + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/>. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#include "xinclude.h" + +typedef struct s_xdmerge { + struct s_xdmerge *next; + /* + * 0 = conflict, + * 1 = no conflict, take first, + * 2 = no conflict, take second. + * 3 = no conflict, take both. + */ + int mode; + /* + * These point at the respective postimages. E.g. <i1,chg1> is + * how side #1 wants to change the common ancestor; if there is no + * overlap, lines before i1 in the postimage of side #1 appear + * in the merge result as a region touched by neither side. + */ + long i1, i2; + long chg1, chg2; + /* + * These point at the preimage; of course there is just one + * preimage, that is from the shared common ancestor. + */ + long i0; + long chg0; +} xdmerge_t; + +static int xdl_append_merge(xdmerge_t **merge, int mode, + long i0, long chg0, + long i1, long chg1, + long i2, long chg2) +{ + xdmerge_t *m = *merge; + if (m && (i1 <= m->i1 + m->chg1 || i2 <= m->i2 + m->chg2)) { + if (mode != m->mode) + m->mode = 0; + m->chg0 = i0 + chg0 - m->i0; + m->chg1 = i1 + chg1 - m->i1; + m->chg2 = i2 + chg2 - m->i2; + } else { + m = xdl_malloc(sizeof(xdmerge_t)); + if (!m) + return -1; + m->next = NULL; + m->mode = mode; + m->i0 = i0; + m->chg0 = chg0; + m->i1 = i1; + m->chg1 = chg1; + m->i2 = i2; + m->chg2 = chg2; + if (*merge) + (*merge)->next = m; + *merge = m; + } + return 0; +} + +static int xdl_cleanup_merge(xdmerge_t *c) +{ + int count = 0; + xdmerge_t *next_c; + + /* were there conflicts? */ + for (; c; c = next_c) { + if (c->mode == 0) + count++; + next_c = c->next; + free(c); + } + return count; +} + +static int xdl_merge_cmp_lines(xdfenv_t *xe1, int i1, xdfenv_t *xe2, int i2, + int line_count, long flags) +{ + int i; + xrecord_t **rec1 = xe1->xdf2.recs + i1; + xrecord_t **rec2 = xe2->xdf2.recs + i2; + + for (i = 0; i < line_count; i++) { + int result = xdl_recmatch(rec1[i]->ptr, rec1[i]->size, + rec2[i]->ptr, rec2[i]->size, flags); + if (!result) + return -1; + } + return 0; +} + +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; + + recs = (use_orig ? xe->xdf1.recs : xe->xdf2.recs) + i; + + if (count < 1) + return 0; + + for (i = 0; i < count; size += recs[i++]->size) + if (dest) + memcpy(dest + size, recs[i]->ptr, recs[i]->size); + 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++; + } + } + return size; +} + +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) +{ + 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 is_cr_needed(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m) +{ + 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, + xdfenv_t *xe2, const char *name2, + const char *name3, + int size, int i, int style, + xdmerge_t *m, char *dest, int marker_size) +{ + 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, 0, + dest ? dest + size : NULL); + + if (!dest) { + size += marker_size + 1 + needs_cr + marker1_size; + } else { + memset(dest + size, '<', marker_size); + size += marker_size; + if (marker1_size) { + dest[size] = ' '; + 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, needs_cr, 1, + dest ? dest + size : NULL); + + if (style == XDL_MERGE_DIFF3) { + /* Shared preimage */ + if (!dest) { + size += marker_size + 1 + needs_cr + marker3_size; + } else { + memset(dest + size, '|', marker_size); + size += marker_size; + if (marker3_size) { + dest[size] = ' '; + 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, needs_cr, 1, + dest ? dest + size : NULL); + } + + if (!dest) { + 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, needs_cr, 1, + dest ? dest + size : NULL); + if (!dest) { + size += marker_size + 1 + needs_cr + marker2_size; + } else { + memset(dest + size, '>', marker_size); + size += marker_size; + if (marker2_size) { + dest[size] = ' '; + memcpy(dest + size + 1, name2, marker2_size - 1); + size += marker2_size; + } + if (needs_cr) + dest[size++] = '\r'; + dest[size++] = '\n'; + } + return size; +} + +static int xdl_fill_merge_buffer(xdfenv_t *xe1, const char *name1, + xdfenv_t *xe2, const char *name2, + const char *ancestor_name, + int favor, + xdmerge_t *m, char *dest, int style, + int marker_size) +{ + int size, i; + + for (size = i = 0; m; m = m->next) { + if (favor && !m->mode) + m->mode = favor; + + if (m->mode == 0) + size = fill_conflict_hunk(xe1, name1, xe2, name2, + ancestor_name, + size, i, style, m, dest, + marker_size); + else if (m->mode & 3) { + /* Before conflicting part */ + size += xdl_recs_copy(xe1, i, m->i1 - i, 0, 0, + dest ? dest + size : NULL); + /* Postimage from side #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, 0, 0, + dest ? dest + size : NULL); + } else + continue; + i = m->i1 + m->chg1; + } + size += xdl_recs_copy(xe1, i, xe1->xdf2.nrec - i, 0, 0, + dest ? dest + size : NULL); + return size; +} + +/* + * Sometimes, changes are not quite identical, but differ in only a few + * lines. Try hard to show only these few lines as conflicting. + */ +static int xdl_refine_conflicts(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m, + xpparam_t const *xpp) +{ + for (; m; m = m->next) { + mmfile_t t1, t2; + xdfenv_t xe; + xdchange_t *xscr, *x; + int i1 = m->i1, i2 = m->i2; + + /* let's handle just the conflicts */ + if (m->mode) + continue; + + /* no sense refining a conflict when one side is empty */ + if (m->chg1 == 0 || m->chg2 == 0) + continue; + + /* + * This probably does not work outside git, since + * we have a very simple mmfile structure. + */ + t1.ptr = (char *)xe1->xdf2.recs[m->i1]->ptr; + t1.size = xe1->xdf2.recs[m->i1 + m->chg1 - 1]->ptr + + xe1->xdf2.recs[m->i1 + m->chg1 - 1]->size - t1.ptr; + t2.ptr = (char *)xe2->xdf2.recs[m->i2]->ptr; + t2.size = xe2->xdf2.recs[m->i2 + m->chg2 - 1]->ptr + + xe2->xdf2.recs[m->i2 + m->chg2 - 1]->size - t2.ptr; + if (xdl_do_diff(&t1, &t2, xpp, &xe) < 0) + return -1; + if (xdl_change_compact(&xe.xdf1, &xe.xdf2, xpp->flags) < 0 || + xdl_change_compact(&xe.xdf2, &xe.xdf1, xpp->flags) < 0 || + xdl_build_script(&xe, &xscr) < 0) { + xdl_free_env(&xe); + return -1; + } + if (!xscr) { + /* If this happens, the changes are identical. */ + xdl_free_env(&xe); + m->mode = 4; + continue; + } + x = xscr; + m->i1 = xscr->i1 + i1; + m->chg1 = xscr->chg1; + m->i2 = xscr->i2 + i2; + m->chg2 = xscr->chg2; + while (xscr->next) { + xdmerge_t *m2 = xdl_malloc(sizeof(xdmerge_t)); + if (!m2) { + xdl_free_env(&xe); + xdl_free_script(x); + return -1; + } + xscr = xscr->next; + m2->next = m->next; + m->next = m2; + m = m2; + m->mode = 0; + m->i1 = xscr->i1 + i1; + m->chg1 = xscr->chg1; + m->i2 = xscr->i2 + i2; + m->chg2 = xscr->chg2; + } + xdl_free_env(&xe); + xdl_free_script(x); + } + return 0; +} + +static int line_contains_alnum(const char *ptr, long size) +{ + while (size--) + if (isalnum((unsigned char)*(ptr++))) + return 1; + return 0; +} + +static int lines_contain_alnum(xdfenv_t *xe, int i, int chg) +{ + for (; chg; chg--, i++) + if (line_contains_alnum(xe->xdf2.recs[i]->ptr, + xe->xdf2.recs[i]->size)) + return 1; + return 0; +} + +/* + * This function merges m and m->next, marking everything between those hunks + * as conflicting, too. + */ +static void xdl_merge_two_conflicts(xdmerge_t *m) +{ + xdmerge_t *next_m = m->next; + m->chg1 = next_m->i1 + next_m->chg1 - m->i1; + m->chg2 = next_m->i2 + next_m->chg2 - m->i2; + m->next = next_m->next; + free(next_m); +} + +/* + * If there are less than 3 non-conflicting lines between conflicts, + * it appears simpler -- because it takes up less (or as many) lines -- + * if the lines are moved into the conflicts. + */ +static int xdl_simplify_non_conflicts(xdfenv_t *xe1, xdmerge_t *m, + int simplify_if_no_alnum) +{ + int result = 0; + + if (!m) + return result; + for (;;) { + xdmerge_t *next_m = m->next; + int begin, end; + + if (!next_m) + return result; + + begin = m->i1 + m->chg1; + end = next_m->i1; + + if (m->mode != 0 || next_m->mode != 0 || + (end - begin > 3 && + (!simplify_if_no_alnum || + lines_contain_alnum(xe1, begin, end - begin)))) { + m = next_m; + } else { + result++; + xdl_merge_two_conflicts(m); + } + } +} + +/* + * level == 0: mark all overlapping changes as conflict + * level == 1: mark overlapping changes as conflict only if not identical + * level == 2: analyze non-identical changes for minimal conflict set + * level == 3: analyze non-identical changes for minimal conflict set, but + * treat hunks not containing any letter or number as conflicting + * + * returns < 0 on error, == 0 for no conflicts, else number of conflicts + */ +static int xdl_do_merge(xdfenv_t *xe1, xdchange_t *xscr1, + xdfenv_t *xe2, xdchange_t *xscr2, + xmparam_t const *xmp, mmbuffer_t *result) +{ + xdmerge_t *changes, *c; + xpparam_t const *xpp = &xmp->xpp; + const char *const ancestor_name = xmp->ancestor; + const char *const name1 = xmp->file1; + const char *const name2 = xmp->file2; + int i0, i1, i2, chg0, chg1, chg2; + int level = xmp->level; + int style = xmp->style; + int favor = xmp->favor; + + if (style == XDL_MERGE_DIFF3) { + /* + * "diff3 -m" output does not make sense for anything + * more aggressive than XDL_MERGE_EAGER. + */ + if (XDL_MERGE_EAGER < level) + level = XDL_MERGE_EAGER; + } + + c = changes = NULL; + + while (xscr1 && xscr2) { + if (!changes) + changes = c; + if (xscr1->i1 + xscr1->chg1 < xscr2->i1) { + i0 = xscr1->i1; + i1 = xscr1->i2; + i2 = xscr2->i2 - xscr2->i1 + xscr1->i1; + chg0 = xscr1->chg1; + chg1 = xscr1->chg2; + chg2 = xscr1->chg1; + if (xdl_append_merge(&c, 1, + i0, chg0, i1, chg1, i2, chg2)) { + xdl_cleanup_merge(changes); + return -1; + } + xscr1 = xscr1->next; + continue; + } + if (xscr2->i1 + xscr2->chg1 < xscr1->i1) { + i0 = xscr2->i1; + i1 = xscr1->i2 - xscr1->i1 + xscr2->i1; + i2 = xscr2->i2; + chg0 = xscr2->chg1; + chg1 = xscr2->chg1; + chg2 = xscr2->chg2; + if (xdl_append_merge(&c, 2, + i0, chg0, i1, chg1, i2, chg2)) { + xdl_cleanup_merge(changes); + return -1; + } + xscr2 = xscr2->next; + continue; + } + if (level == XDL_MERGE_MINIMAL || xscr1->i1 != xscr2->i1 || + xscr1->chg1 != xscr2->chg1 || + xscr1->chg2 != xscr2->chg2 || + xdl_merge_cmp_lines(xe1, xscr1->i2, + xe2, xscr2->i2, + xscr1->chg2, xpp->flags)) { + /* conflict */ + int off = xscr1->i1 - xscr2->i1; + int ffo = off + xscr1->chg1 - xscr2->chg1; + + i0 = xscr1->i1; + i1 = xscr1->i2; + i2 = xscr2->i2; + if (off > 0) { + i0 -= off; + i1 -= off; + } + else + i2 += off; + chg0 = xscr1->i1 + xscr1->chg1 - i0; + chg1 = xscr1->i2 + xscr1->chg2 - i1; + chg2 = xscr2->i2 + xscr2->chg2 - i2; + if (ffo < 0) { + chg0 -= ffo; + chg1 -= ffo; + } else + chg2 += ffo; + if (xdl_append_merge(&c, 0, + i0, chg0, i1, chg1, i2, chg2)) { + xdl_cleanup_merge(changes); + return -1; + } + } + + i1 = xscr1->i1 + xscr1->chg1; + i2 = xscr2->i1 + xscr2->chg1; + + if (i1 >= i2) + xscr2 = xscr2->next; + if (i2 >= i1) + xscr1 = xscr1->next; + } + while (xscr1) { + if (!changes) + changes = c; + i0 = xscr1->i1; + i1 = xscr1->i2; + i2 = xscr1->i1 + xe2->xdf2.nrec - xe2->xdf1.nrec; + chg0 = xscr1->chg1; + chg1 = xscr1->chg2; + chg2 = xscr1->chg1; + if (xdl_append_merge(&c, 1, + i0, chg0, i1, chg1, i2, chg2)) { + xdl_cleanup_merge(changes); + return -1; + } + xscr1 = xscr1->next; + } + while (xscr2) { + if (!changes) + changes = c; + i0 = xscr2->i1; + i1 = xscr2->i1 + xe1->xdf2.nrec - xe1->xdf1.nrec; + i2 = xscr2->i2; + chg0 = xscr2->chg1; + chg1 = xscr2->chg1; + chg2 = xscr2->chg2; + if (xdl_append_merge(&c, 2, + i0, chg0, i1, chg1, i2, chg2)) { + xdl_cleanup_merge(changes); + return -1; + } + xscr2 = xscr2->next; + } + if (!changes) + changes = c; + /* refine conflicts */ + if (XDL_MERGE_ZEALOUS <= level && + (xdl_refine_conflicts(xe1, xe2, changes, xpp) < 0 || + xdl_simplify_non_conflicts(xe1, changes, + XDL_MERGE_ZEALOUS < level) < 0)) { + xdl_cleanup_merge(changes); + return -1; + } + /* output */ + if (result) { + int marker_size = xmp->marker_size; + int size = xdl_fill_merge_buffer(xe1, name1, xe2, name2, + ancestor_name, + favor, changes, NULL, style, + marker_size); + result->ptr = xdl_malloc(size); + if (!result->ptr) { + xdl_cleanup_merge(changes); + return -1; + } + result->size = size; + xdl_fill_merge_buffer(xe1, name1, xe2, name2, + ancestor_name, favor, changes, + result->ptr, style, marker_size); + } + return xdl_cleanup_merge(changes); +} + +int xdl_merge(mmfile_t *orig, mmfile_t *mf1, mmfile_t *mf2, + xmparam_t const *xmp, mmbuffer_t *result) +{ + xdchange_t *xscr1, *xscr2; + xdfenv_t xe1, xe2; + int status; + xpparam_t const *xpp = &xmp->xpp; + + result->ptr = NULL; + result->size = 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 || + xdl_change_compact(&xe1.xdf2, &xe1.xdf1, xpp->flags) < 0 || + xdl_build_script(&xe1, &xscr1) < 0) { + xdl_free_env(&xe1); + return -1; + } + 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; + } + status = 0; + if (!xscr1) { + result->ptr = xdl_malloc(mf2->size); + memcpy(result->ptr, mf2->ptr, mf2->size); + result->size = mf2->size; + } else if (!xscr2) { + result->ptr = xdl_malloc(mf1->size); + memcpy(result->ptr, mf1->ptr, mf1->size); + result->size = mf1->size; + } else { + status = xdl_do_merge(&xe1, xscr1, + &xe2, xscr2, + xmp, result); + } + xdl_free_script(xscr1); + xdl_free_script(xscr2); + + xdl_free_env(&xe1); + xdl_free_env(&xe2); + + return status; +} diff --git a/xdiff/xpatience.c b/xdiff/xpatience.c new file mode 100644 index 000000000000..3c5601b602a2 --- /dev/null +++ b/xdiff/xpatience.c @@ -0,0 +1,388 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * 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 + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/>. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ +#include "xinclude.h" + +/* + * The basic idea of patience diff is to find lines that are unique in + * both files. These are intuitively the ones that we want to see as + * common lines. + * + * The maximal ordered sequence of such line pairs (where ordered means + * that the order in the sequence agrees with the order of the lines in + * both files) naturally defines an initial set of common lines. + * + * Now, the algorithm tries to extend the set of common lines by growing + * the line ranges where the files have identical lines. + * + * Between those common lines, the patience diff algorithm is applied + * recursively, until no unique line pairs can be found; these line ranges + * are handled by the well-known Myers algorithm. + */ + +#define NON_UNIQUE ULONG_MAX + +/* + * This is a hash mapping from line hash to line numbers in the first and + * second file. + */ +struct hashmap { + int nr, alloc; + struct entry { + unsigned long hash; + /* + * 0 = unused entry, 1 = first line, 2 = second, etc. + * line2 is NON_UNIQUE if the line is not unique + * in either the first or the second file. + */ + unsigned long line1, line2; + /* + * "next" & "previous" are used for the longest common + * sequence; + * initially, "next" reflects only the order in file1. + */ + struct entry *next, *previous; + + /* + * If 1, this entry can serve as an anchor. See + * Documentation/diff-options.txt for more information. + */ + unsigned anchor : 1; + } *entries, *first, *last; + /* were common records found? */ + unsigned long has_matches; + mmfile_t *file1, *file2; + xdfenv_t *env; + xpparam_t const *xpp; +}; + +static int is_anchor(xpparam_t const *xpp, const char *line) +{ + int i; + for (i = 0; i < xpp->anchors_nr; i++) { + if (!strncmp(line, xpp->anchors[i], strlen(xpp->anchors[i]))) + return 1; + } + return 0; +} + +/* The argument "pass" is 1 for the first file, 2 for the second. */ +static void insert_record(xpparam_t const *xpp, int line, struct hashmap *map, + int pass) +{ + xrecord_t **records = pass == 1 ? + map->env->xdf1.recs : map->env->xdf2.recs; + xrecord_t *record = records[line - 1], *other; + /* + * After xdl_prepare_env() (or more precisely, due to + * xdl_classify_record()), the "ha" member of the records (AKA lines) + * is _not_ the hash anymore, but a linearized version of it. In + * other words, the "ha" member is guaranteed to start with 0 and + * the second record's ha can only be 0 or 1, etc. + * + * So we multiply ha by 2 in the hope that the hashing was + * "unique enough". + */ + int index = (int)((record->ha << 1) % map->alloc); + + while (map->entries[index].line1) { + other = map->env->xdf1.recs[map->entries[index].line1 - 1]; + if (map->entries[index].hash != record->ha || + !xdl_recmatch(record->ptr, record->size, + other->ptr, other->size, + map->xpp->flags)) { + if (++index >= map->alloc) + index = 0; + continue; + } + if (pass == 2) + map->has_matches = 1; + if (pass == 1 || map->entries[index].line2) + map->entries[index].line2 = NON_UNIQUE; + else + map->entries[index].line2 = line; + return; + } + if (pass == 2) + return; + map->entries[index].line1 = line; + map->entries[index].hash = record->ha; + map->entries[index].anchor = is_anchor(xpp, map->env->xdf1.recs[line - 1]->ptr); + if (!map->first) + map->first = map->entries + index; + if (map->last) { + map->last->next = map->entries + index; + map->entries[index].previous = map->last; + } + map->last = map->entries + index; + map->nr++; +} + +/* + * This function has to be called for each recursion into the inter-hunk + * parts, as previously non-unique lines can become unique when being + * restricted to a smaller part of the files. + * + * It is assumed that env has been prepared using xdl_prepare(). + */ +static int fill_hashmap(mmfile_t *file1, mmfile_t *file2, + xpparam_t const *xpp, xdfenv_t *env, + struct hashmap *result, + int line1, int count1, int line2, int count2) +{ + result->file1 = file1; + result->file2 = file2; + result->xpp = xpp; + result->env = env; + + /* We know exactly how large we want the hash map */ + result->alloc = count1 * 2; + result->entries = (struct entry *) + xdl_malloc(result->alloc * sizeof(struct entry)); + if (!result->entries) + return -1; + memset(result->entries, 0, result->alloc * sizeof(struct entry)); + + /* First, fill with entries from the first file */ + while (count1--) + insert_record(xpp, line1++, result, 1); + + /* Then search for matches in the second file */ + while (count2--) + insert_record(xpp, line2++, result, 2); + + return 0; +} + +/* + * Find the longest sequence with a smaller last element (meaning a smaller + * line2, as we construct the sequence with entries ordered by line1). + */ +static int binary_search(struct entry **sequence, int longest, + struct entry *entry) +{ + int left = -1, right = longest; + + while (left + 1 < right) { + int middle = left + (right - left) / 2; + /* by construction, no two entries can be equal */ + if (sequence[middle]->line2 > entry->line2) + right = middle; + else + left = middle; + } + /* return the index in "sequence", _not_ the sequence length */ + return left; +} + +/* + * The idea is to start with the list of common unique lines sorted by + * the order in file1. For each of these pairs, the longest (partial) + * sequence whose last element's line2 is smaller is determined. + * + * For efficiency, the sequences are kept in a list containing exactly one + * item per sequence length: the sequence with the smallest last + * element (in terms of line2). + */ +static struct entry *find_longest_common_sequence(struct hashmap *map) +{ + struct entry **sequence = xdl_malloc(map->nr * sizeof(struct entry *)); + int longest = 0, i; + struct entry *entry; + + /* + * If not -1, this entry in sequence must never be overridden. + * Therefore, overriding entries before this has no effect, so + * do not do that either. + */ + int anchor_i = -1; + + for (entry = map->first; entry; entry = entry->next) { + if (!entry->line2 || entry->line2 == NON_UNIQUE) + continue; + i = binary_search(sequence, longest, entry); + entry->previous = i < 0 ? NULL : sequence[i]; + ++i; + if (i <= anchor_i) + continue; + sequence[i] = entry; + if (entry->anchor) { + anchor_i = i; + longest = anchor_i + 1; + } else if (i == longest) { + longest++; + } + } + + /* No common unique lines were found */ + if (!longest) { + xdl_free(sequence); + return NULL; + } + + /* Iterate starting at the last element, adjusting the "next" members */ + entry = sequence[longest - 1]; + entry->next = NULL; + while (entry->previous) { + entry->previous->next = entry; + entry = entry->previous; + } + xdl_free(sequence); + return entry; +} + +static int match(struct hashmap *map, int line1, int line2) +{ + xrecord_t *record1 = map->env->xdf1.recs[line1 - 1]; + xrecord_t *record2 = map->env->xdf2.recs[line2 - 1]; + return xdl_recmatch(record1->ptr, record1->size, + record2->ptr, record2->size, map->xpp->flags); +} + +static int patience_diff(mmfile_t *file1, mmfile_t *file2, + xpparam_t const *xpp, xdfenv_t *env, + int line1, int count1, int line2, int count2); + +static int walk_common_sequence(struct hashmap *map, struct entry *first, + int line1, int count1, int line2, int count2) +{ + int end1 = line1 + count1, end2 = line2 + count2; + int next1, next2; + + for (;;) { + /* Try to grow the line ranges of common lines */ + if (first) { + next1 = first->line1; + next2 = first->line2; + while (next1 > line1 && next2 > line2 && + match(map, next1 - 1, next2 - 1)) { + next1--; + next2--; + } + } else { + next1 = end1; + next2 = end2; + } + while (line1 < next1 && line2 < next2 && + match(map, line1, line2)) { + line1++; + line2++; + } + + /* Recurse */ + if (next1 > line1 || next2 > line2) { + struct hashmap submap; + + memset(&submap, 0, sizeof(submap)); + if (patience_diff(map->file1, map->file2, + map->xpp, map->env, + line1, next1 - line1, + line2, next2 - line2)) + return -1; + } + + if (!first) + return 0; + + while (first->next && + first->next->line1 == first->line1 + 1 && + first->next->line2 == first->line2 + 1) + first = first->next; + + line1 = first->line1 + 1; + line2 = first->line2 + 1; + + first = first->next; + } +} + +static int fall_back_to_classic_diff(struct hashmap *map, + int line1, int count1, int line2, int count2) +{ + xpparam_t xpp; + xpp.flags = map->xpp->flags & ~XDF_DIFF_ALGORITHM_MASK; + + return xdl_fall_back_diff(map->env, &xpp, + line1, count1, line2, count2); +} + +/* + * Recursively find the longest common sequence of unique lines, + * and if none was found, ask xdl_do_diff() to do the job. + * + * This function assumes that env was prepared with xdl_prepare_env(). + */ +static int patience_diff(mmfile_t *file1, mmfile_t *file2, + xpparam_t const *xpp, xdfenv_t *env, + int line1, int count1, int line2, int count2) +{ + struct hashmap map; + struct entry *first; + int result = 0; + + /* trivial case: one side is empty */ + 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(&map, 0, sizeof(map)); + if (fill_hashmap(file1, file2, xpp, env, &map, + line1, count1, line2, count2)) + return -1; + + /* are there any matching lines at all? */ + if (!map.has_matches) { + while(count1--) + env->xdf1.rchg[line1++ - 1] = 1; + while(count2--) + env->xdf2.rchg[line2++ - 1] = 1; + xdl_free(map.entries); + return 0; + } + + first = find_longest_common_sequence(&map); + if (first) + result = walk_common_sequence(&map, first, + line1, count1, line2, count2); + else + result = fall_back_to_classic_diff(&map, + line1, count1, line2, count2); + + xdl_free(map.entries); + return result; +} + +int xdl_do_patience_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; + + /* environment is cleaned up in xdl_diff() */ + return patience_diff(file1, file2, xpp, env, + 1, env->xdf1.nrec, 1, env->xdf2.nrec); +} diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c new file mode 100644 index 000000000000..abeb8fb84e6d --- /dev/null +++ b/xdiff/xprepare.c @@ -0,0 +1,483 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/>. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#include "xinclude.h" + + +#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 { + struct s_xdlclass *next; + unsigned long ha; + char const *line; + long size; + long idx; + long len1, len2; +} xdlclass_t; + +typedef struct s_xdlclassifier { + unsigned int hbits; + long hsize; + xdlclass_t **rchash; + chastore_t ncha; + xdlclass_t **rcrecs; + long alloc; + long count; + long flags; +} xdlclassifier_t; + + + + +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(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(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(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2); + + + + +static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags) { + cf->flags = flags; + + cf->hbits = xdl_hashbits((unsigned int) size); + cf->hsize = 1 << cf->hbits; + + if (xdl_cha_init(&cf->ncha, sizeof(xdlclass_t), size / 4 + 1) < 0) { + + return -1; + } + if (!(cf->rchash = (xdlclass_t **) xdl_malloc(cf->hsize * sizeof(xdlclass_t *)))) { + + xdl_cha_free(&cf->ncha); + return -1; + } + 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; + + return 0; +} + + +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(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); + for (rcrec = cf->rchash[hi]; rcrec; rcrec = rcrec->next) + if (rcrec->ha == rec->ha && + xdl_recmatch(rcrec->line, rcrec->size, + rec->ptr, rec->size, cf->flags)) + break; + + if (!rcrec) { + if (!(rcrec = xdl_cha_alloc(&cf->ncha))) { + + 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); + rec->next = rhash[hi]; + rhash[hi] = rec; + + return 0; +} + + +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 nrec, hsize, bsize; + unsigned long hav; + char const *blk, *cur, *top, *prev; + xrecord_t *crec; + xrecord_t **recs, **rrecs; + xrecord_t **rhash; + unsigned long *ha; + char *rchg; + long *rindex; + + 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 *)); + } + + nrec = 0; + if ((cur = blk = xdl_mmfile_first(mf, &bsize)) != NULL) { + 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 *)))) + goto abort; + recs = rrecs; + } + if (!(crec = xdl_cha_alloc(&xdf->rcha))) + goto abort; + crec->ptr = prev; + crec->size = (long) (cur - prev); + crec->ha = hav; + recs[nrec++] = crec; + + 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)))) + goto abort; + memset(rchg, 0, (nrec + 2) * sizeof(char)); + + 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; + xdf->hbits = hbits; + xdf->rhash = rhash; + xdf->rchg = rchg + 1; + xdf->rindex = rindex; + xdf->nreff = 0; + xdf->ha = ha; + xdf->dstart = 0; + 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; +} + + +static void xdl_free_ctx(xdfile_t *xdf) { + + xdl_free(xdf->rhash); + xdl_free(xdf->rindex); + xdl_free(xdf->rchg - 1); + xdl_free(xdf->ha); + xdl_free(xdf->recs); + xdl_cha_free(&xdf->rcha); +} + + +int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, + xdfenv_t *xe) { + long enl1, enl2, sample; + xdlclassifier_t cf; + + 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); + + 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(1, mf1, enl1, xpp, &cf, &xe->xdf1) < 0) { + + xdl_free_classifier(&cf); + return -1; + } + if (xdl_prepare_ctx(2, mf2, enl2, xpp, &cf, &xe->xdf2) < 0) { + + xdl_free_ctx(&xe->xdf1); + xdl_free_classifier(&cf); + return -1; + } + + 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; +} + + +void xdl_free_env(xdfenv_t *xe) { + + xdl_free_ctx(&xe->xdf2); + xdl_free_ctx(&xe->xdf1); +} + + +static int xdl_clean_mmatch(char const *dis, long i, long s, long e) { + long r, rdis0, rpdis0, rdis1, rpdis1; + + /* + * Limits the window the is examined during the similar-lines + * scan. The loops below stops when dis[i - r] == 1 (line that + * has no match), but there are corner cases where the loop + * proceed all the way to the extremities by causing huge + * performance penalties in case of big files. + */ + if (i - s > XDL_SIMSCAN_WINDOW) + s = i - XDL_SIMSCAN_WINDOW; + if (e - i > XDL_SIMSCAN_WINDOW) + e = i + XDL_SIMSCAN_WINDOW; + + /* + * Scans the lines before 'i' to find a run of lines that either + * have no match (dis[j] == 0) or have multiple matches (dis[j] > 1). + * Note that we always call this function with dis[i] > 1, so the + * current line (i) is already a multimatch line. + */ + for (r = 1, rdis0 = 0, rpdis0 = 1; (i - r) >= s; r++) { + if (!dis[i - r]) + rdis0++; + else if (dis[i - r] == 2) + rpdis0++; + else + break; + } + /* + * If the run before the line 'i' found only multimatch lines, we + * return 0 and hence we don't make the current line (i) discarded. + * We want to discard multimatch lines only when they appear in the + * middle of runs with nomatch lines (dis[j] == 0). + */ + if (rdis0 == 0) + return 0; + for (r = 1, rdis1 = 0, rpdis1 = 1; (i + r) <= e; r++) { + if (!dis[i + r]) + rdis1++; + else if (dis[i + r] == 2) + rpdis1++; + else + break; + } + /* + * If the run after the line 'i' found only multimatch lines, we + * return 0 and hence we don't make the current line (i) discarded. + */ + if (rdis1 == 0) + return 0; + rdis1 += rdis0; + rpdis1 += rpdis0; + + return rpdis1 * XDL_KPDIS_RUN < (rpdis1 + rdis1); +} + + +/* + * Try to reduce the problem complexity, discard records that have no + * 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(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) { + long i, nm, nreff, mlim; + xrecord_t **recs; + xdlclass_t *rcrec; + char *dis, *dis1, *dis2; + + if (!(dis = (char *) xdl_malloc(xdf1->nrec + xdf2->nrec + 2))) { + + return -1; + } + memset(dis, 0, xdf1->nrec + xdf2->nrec + 2); + dis1 = dis; + dis2 = dis1 + xdf1->nrec + 1; + + 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++) { + 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++) { + rcrec = cf->rcrecs[(*recs)->ha]; + nm = rcrec ? rcrec->len1 : 0; + dis2[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1; + } + + for (nreff = 0, i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart]; + i <= xdf1->dend; i++, recs++) { + if (dis1[i] == 1 || + (dis1[i] == 2 && !xdl_clean_mmatch(dis1, i, xdf1->dstart, xdf1->dend))) { + xdf1->rindex[nreff] = i; + xdf1->ha[nreff] = (*recs)->ha; + nreff++; + } else + xdf1->rchg[i] = 1; + } + xdf1->nreff = nreff; + + for (nreff = 0, i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart]; + i <= xdf2->dend; i++, recs++) { + if (dis2[i] == 1 || + (dis2[i] == 2 && !xdl_clean_mmatch(dis2, i, xdf2->dstart, xdf2->dend))) { + xdf2->rindex[nreff] = i; + xdf2->ha[nreff] = (*recs)->ha; + nreff++; + } else + xdf2->rchg[i] = 1; + } + xdf2->nreff = nreff; + + xdl_free(dis); + + return 0; +} + + +/* + * Early trim initial and terminal matching records. + */ +static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2) { + long i, lim; + xrecord_t **recs1, **recs2; + + recs1 = xdf1->recs; + recs2 = xdf2->recs; + for (i = 0, lim = XDL_MIN(xdf1->nrec, xdf2->nrec); i < lim; + i++, recs1++, recs2++) + if ((*recs1)->ha != (*recs2)->ha) + break; + + xdf1->dstart = xdf2->dstart = i; + + recs1 = xdf1->recs + xdf1->nrec - 1; + recs2 = xdf2->recs + xdf2->nrec - 1; + for (lim -= i, i = 0; i < lim; i++, recs1--, recs2--) + if ((*recs1)->ha != (*recs2)->ha) + break; + + xdf1->dend = xdf1->nrec - i - 1; + xdf2->dend = xdf2->nrec - i - 1; + + return 0; +} + + +static int xdl_optimize_ctxs(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) { + + if (xdl_trim_ends(xdf1, xdf2) < 0 || + xdl_cleanup_records(cf, xdf1, xdf2) < 0) { + + return -1; + } + + return 0; +} diff --git a/xdiff/xprepare.h b/xdiff/xprepare.h new file mode 100644 index 000000000000..947d9fc1bb8c --- /dev/null +++ b/xdiff/xprepare.h @@ -0,0 +1,34 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/>. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XPREPARE_H) +#define XPREPARE_H + + + +int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, + xdfenv_t *xe); +void xdl_free_env(xdfenv_t *xe); + + + +#endif /* #if !defined(XPREPARE_H) */ diff --git a/xdiff/xtypes.h b/xdiff/xtypes.h new file mode 100644 index 000000000000..8442bd436efe --- /dev/null +++ b/xdiff/xtypes.h @@ -0,0 +1,67 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/>. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XTYPES_H) +#define XTYPES_H + + + +typedef struct s_chanode { + struct s_chanode *next; + long icurr; +} chanode_t; + +typedef struct s_chastore { + chanode_t *head, *tail; + long isize, nsize; + chanode_t *ancur; + chanode_t *sncur; + long scurr; +} chastore_t; + +typedef struct s_xrecord { + struct s_xrecord *next; + char const *ptr; + long size; + unsigned long ha; +} xrecord_t; + +typedef struct s_xdfile { + chastore_t rcha; + long nrec; + unsigned int hbits; + xrecord_t **rhash; + long dstart, dend; + xrecord_t **recs; + char *rchg; + long *rindex; + long nreff; + unsigned long *ha; +} xdfile_t; + +typedef struct s_xdfenv { + xdfile_t xdf1, xdf2; +} xdfenv_t; + + + +#endif /* #if !defined(XTYPES_H) */ diff --git a/xdiff/xutils.c b/xdiff/xutils.c new file mode 100644 index 000000000000..cfa6e2220ffd --- /dev/null +++ b/xdiff/xutils.c @@ -0,0 +1,434 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/>. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#include "xinclude.h" + + +long xdl_bogosqrt(long n) { + long i; + + /* + * Classical integer square root approximation using shifts. + */ + for (i = 1; n > 0; n >>= 2) + i <<= 1; + + return i; +} + + +int xdl_emit_diffrec(char const *rec, long size, char const *pre, long psize, + xdemitcb_t *ecb) { + int i = 2; + mmbuffer_t mb[3]; + + mb[0].ptr = (char *) pre; + mb[0].size = psize; + mb[1].ptr = (char *) rec; + mb[1].size = size; + if (size > 0 && rec[size - 1] != '\n') { + mb[2].ptr = (char *) "\n\\ No newline at end of file\n"; + mb[2].size = strlen(mb[2].ptr); + i++; + } + if (ecb->out_line(ecb->priv, mb, i) < 0) { + + return -1; + } + + return 0; +} + +void *xdl_mmfile_first(mmfile_t *mmf, long *size) +{ + *size = mmf->size; + return mmf->ptr; +} + + +long xdl_mmfile_size(mmfile_t *mmf) +{ + return mmf->size; +} + + +int xdl_cha_init(chastore_t *cha, long isize, long icount) { + + cha->head = cha->tail = NULL; + cha->isize = isize; + cha->nsize = icount * isize; + cha->ancur = cha->sncur = NULL; + cha->scurr = 0; + + return 0; +} + + +void xdl_cha_free(chastore_t *cha) { + chanode_t *cur, *tmp; + + for (cur = cha->head; (tmp = cur) != NULL;) { + cur = cur->next; + xdl_free(tmp); + } +} + + +void *xdl_cha_alloc(chastore_t *cha) { + chanode_t *ancur; + void *data; + + if (!(ancur = cha->ancur) || ancur->icurr == cha->nsize) { + if (!(ancur = (chanode_t *) xdl_malloc(sizeof(chanode_t) + cha->nsize))) { + + return NULL; + } + ancur->icurr = 0; + ancur->next = NULL; + if (cha->tail) + cha->tail->next = ancur; + if (!cha->head) + cha->head = ancur; + cha->tail = ancur; + cha->ancur = ancur; + } + + data = (char *) ancur + sizeof(chanode_t) + ancur->icurr; + ancur->icurr += cha->isize; + + return data; +} + +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 < sample && cur < top; ) { + nl++; + if (!(cur = memchr(cur, '\n', top - cur))) + cur = top; + else + cur++; + } + tsize += (long) (cur - data); + } + + if (nl && tsize) + nl = xdl_mmfile_size(mf) / (tsize / nl); + + 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); +} + +/* + * Have we eaten everything on the line, except for an optional + * CR at the very end? + */ +static int ends_with_optional_cr(const char *l, long s, long i) +{ + int complete = s && l[s-1] == '\n'; + + if (complete) + s--; + if (s == i) + return 1; + /* do not ignore CR at the end of an incomplete line */ + if (complete && s == i + 1 && l[i] == '\r') + return 1; + return 0; +} + +int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags) +{ + int i1, i2; + + if (s1 == s2 && !memcmp(l1, l2, s1)) + return 1; + if (!(flags & XDF_WHITESPACE_FLAGS)) + return 0; + + i1 = 0; + i2 = 0; + + /* + * -w matches everything that matches with -b, and -b in turn + * matches everything that matches with --ignore-space-at-eol, + * which in turn matches everything that matches with --ignore-cr-at-eol. + * + * Each flavor of ignoring needs different logic to skip whitespaces + * while we have both sides to compare. + */ + if (flags & XDF_IGNORE_WHITESPACE) { + goto skip_ws; + while (i1 < s1 && i2 < s2) { + if (l1[i1++] != l2[i2++]) + return 0; + skip_ws: + while (i1 < s1 && XDL_ISSPACE(l1[i1])) + i1++; + while (i2 < s2 && XDL_ISSPACE(l2[i2])) + i2++; + } + } else if (flags & XDF_IGNORE_WHITESPACE_CHANGE) { + while (i1 < s1 && i2 < s2) { + if (XDL_ISSPACE(l1[i1]) && XDL_ISSPACE(l2[i2])) { + /* Skip matching spaces and try again */ + while (i1 < s1 && XDL_ISSPACE(l1[i1])) + i1++; + while (i2 < s2 && XDL_ISSPACE(l2[i2])) + i2++; + continue; + } + if (l1[i1++] != l2[i2++]) + return 0; + } + } else if (flags & XDF_IGNORE_WHITESPACE_AT_EOL) { + while (i1 < s1 && i2 < s2 && l1[i1] == l2[i2]) { + i1++; + i2++; + } + } else if (flags & XDF_IGNORE_CR_AT_EOL) { + /* Find the first difference and see how the line ends */ + while (i1 < s1 && i2 < s2 && l1[i1] == l2[i2]) { + i1++; + i2++; + } + return (ends_with_optional_cr(l1, s1, i1) && + ends_with_optional_cr(l2, s2, i2)); + } + + /* + * After running out of one side, the remaining side must have + * nothing but whitespace for the lines to match. Note that + * ignore-whitespace-at-eol case may break out of the loop + * while there still are characters remaining on both lines. + */ + if (i1 < s1) { + while (i1 < s1 && XDL_ISSPACE(l1[i1])) + i1++; + if (s1 != i1) + return 0; + } + if (i2 < s2) { + while (i2 < s2 && XDL_ISSPACE(l2[i2])) + i2++; + return (s2 == i2); + } + return 1; +} + +static unsigned long xdl_hash_record_with_whitespace(char const **data, + char const *top, long flags) { + unsigned long ha = 5381; + char const *ptr = *data; + int cr_at_eol_only = (flags & XDF_WHITESPACE_FLAGS) == XDF_IGNORE_CR_AT_EOL; + + for (; ptr < top && *ptr != '\n'; ptr++) { + if (cr_at_eol_only) { + /* do not ignore CR at the end of an incomplete line */ + if (*ptr == '\r' && + (ptr + 1 < top && ptr[1] == '\n')) + continue; + } + else if (XDL_ISSPACE(*ptr)) { + const char *ptr2 = ptr; + int at_eol; + while (ptr + 1 < top && XDL_ISSPACE(ptr[1]) + && ptr[1] != '\n') + ptr++; + at_eol = (top <= ptr + 1 || ptr[1] == '\n'); + if (flags & XDF_IGNORE_WHITESPACE) + ; /* already handled */ + else if (flags & XDF_IGNORE_WHITESPACE_CHANGE + && !at_eol) { + ha += (ha << 5); + ha ^= (unsigned long) ' '; + } + else if (flags & XDF_IGNORE_WHITESPACE_AT_EOL + && !at_eol) { + while (ptr2 != ptr + 1) { + ha += (ha << 5); + ha ^= (unsigned long) *ptr2; + ptr2++; + } + } + continue; + } + ha += (ha << 5); + ha ^= (unsigned long) *ptr; + } + *data = ptr < top ? ptr + 1: ptr; + + return ha; +} + +unsigned long xdl_hash_record(char const **data, char const *top, long flags) { + unsigned long ha = 5381; + char const *ptr = *data; + + if (flags & XDF_WHITESPACE_FLAGS) + return xdl_hash_record_with_whitespace(data, top, flags); + + for (; ptr < top && *ptr != '\n'; ptr++) { + ha += (ha << 5); + ha ^= (unsigned long) *ptr; + } + *data = ptr < top ? ptr + 1: ptr; + + return ha; +} + +unsigned int xdl_hashbits(unsigned int size) { + unsigned int val = 1, bits = 0; + + for (; val < size && bits < CHAR_BIT * sizeof(unsigned int); val <<= 1, bits++); + return bits ? bits: 1; +} + + +int xdl_num_out(char *out, long val) { + char *ptr, *str = out; + char buf[32]; + + ptr = buf + sizeof(buf) - 1; + *ptr = '\0'; + if (val < 0) { + *--ptr = '-'; + val = -val; + } + for (; val && ptr > buf; val /= 10) + *--ptr = "0123456789"[val % 10]; + if (*ptr) + for (; *ptr; ptr++, str++) + *str = *ptr; + else + *str++ = '0'; + *str = '\0'; + + return str - out; +} + +static int xdl_format_hunk_hdr(long s1, long c1, long s2, long c2, + const char *func, long funclen, + xdemitcb_t *ecb) { + int nb = 0; + mmbuffer_t mb; + char buf[128]; + + memcpy(buf, "@@ -", 4); + nb += 4; + + nb += xdl_num_out(buf + nb, c1 ? s1: s1 - 1); + + if (c1 != 1) { + memcpy(buf + nb, ",", 1); + nb += 1; + + nb += xdl_num_out(buf + nb, c1); + } + + memcpy(buf + nb, " +", 2); + nb += 2; + + nb += xdl_num_out(buf + nb, c2 ? s2: s2 - 1); + + if (c2 != 1) { + memcpy(buf + nb, ",", 1); + nb += 1; + + nb += xdl_num_out(buf + nb, c2); + } + + memcpy(buf + nb, " @@", 3); + nb += 3; + if (func && funclen) { + buf[nb++] = ' '; + if (funclen > sizeof(buf) - nb - 1) + funclen = sizeof(buf) - nb - 1; + memcpy(buf + nb, func, funclen); + nb += funclen; + } + buf[nb++] = '\n'; + + mb.ptr = buf; + mb.size = nb; + if (ecb->out_line(ecb->priv, &mb, 1) < 0) + return -1; + return 0; +} + +int xdl_emit_hunk_hdr(long s1, long c1, long s2, long c2, + const char *func, long funclen, + xdemitcb_t *ecb) { + if (!ecb->out_hunk) + return xdl_format_hunk_hdr(s1, c1, s2, c2, func, funclen, ecb); + if (ecb->out_hunk(ecb->priv, + c1 ? s1 : s1 - 1, c1, + c2 ? s2 : s2 - 1, c2, + func, funclen) < 0) + return -1; + 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 new file mode 100644 index 000000000000..fba7bae03c78 --- /dev/null +++ b/xdiff/xutils.h @@ -0,0 +1,47 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/>. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XUTILS_H) +#define XUTILS_H + + + +long xdl_bogosqrt(long n); +int xdl_emit_diffrec(char const *rec, long size, char const *pre, long psize, + xdemitcb_t *ecb); +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); +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); +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); + + + +#endif /* #if !defined(XUTILS_H) */ |