X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;f=xdiff%2Fxutils.c;h=0de084e53f5144153373cc66cae7b523b4ae2812;hb=35a71f1402b40b580d985a9d7e5fb1c9ec4d0232;hp=04ad468702209b77427e635370d41001986042ce;hpb=77f143bf3e218857ec8e5244d7e862e8e0c1a041;p=git.git diff --git a/xdiff/xutils.c b/xdiff/xutils.c index 04ad46870..0de084e53 100644 --- a/xdiff/xutils.c +++ b/xdiff/xutils.c @@ -24,10 +24,6 @@ -#define XDL_GUESS_NLINES 256 - - - long xdl_bogosqrt(long n) { long i; @@ -71,12 +67,6 @@ void *xdl_mmfile_first(mmfile_t *mmf, long *size) } -void *xdl_mmfile_next(mmfile_t *mmf, long *size) -{ - return NULL; -} - - long xdl_mmfile_size(mmfile_t *mmf) { return mmf->size; @@ -159,18 +149,12 @@ void *xdl_cha_next(chastore_t *cha) { } -long xdl_guess_lines(mmfile_t *mf) { +long xdl_guess_lines(mmfile_t *mf, long sample) { long nl = 0, size, tsize = 0; char const *data, *cur, *top; if ((cur = data = xdl_mmfile_first(mf, &size)) != NULL) { - for (top = data + size; nl < XDL_GUESS_NLINES;) { - if (cur >= top) { - tsize += (long) (cur - data); - if (!(cur = data = xdl_mmfile_next(mf, &size))) - break; - top = data + size; - } + for (top = data + size; nl < sample && cur < top; ) { nl++; if (!(cur = memchr(cur, '\n', top - cur))) cur = top; @@ -190,48 +174,68 @@ 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. + * + * Each flavor of ignoring needs different logic to skip whitespaces + * while we have both sides to compare. + */ if (flags & XDF_IGNORE_WHITESPACE) { - for (i1 = i2 = 0; i1 < s1 && i2 < s2; ) { - if (isspace(l1[i1])) - while (isspace(l1[i1]) && i1 < s1) - i1++; - if (isspace(l2[i2])) - while (isspace(l2[i2]) && i2 < s2) - i2++; - if (i1 < s1 && i2 < s2 && l1[i1++] != l2[i2++]) + 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++; } - return (i1 >= s1 && i2 >= s2); } else if (flags & XDF_IGNORE_WHITESPACE_CHANGE) { - for (i1 = i2 = 0; i1 < s1 && i2 < s2; ) { - if (isspace(l1[i1])) { - if (!isspace(l2[i2])) - return 0; - while (isspace(l1[i1]) && i1 < s1) + 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 (isspace(l2[i2]) && i2 < s2) + while (i2 < s2 && XDL_ISSPACE(l2[i2])) i2++; - } else if (l1[i1++] != l2[i2++]) + continue; + } + if (l1[i1++] != l2[i2++]) return 0; } - return (i1 >= s1 && i2 >= s2); } else if (flags & XDF_IGNORE_WHITESPACE_AT_EOL) { - for (i1 = i2 = 0; i1 < s1 && i2 < s2; ) { - if (l1[i1] != l2[i2]) { - while (i1 < s1 && isspace(l1[i1])) - i1++; - while (i2 < s2 && isspace(l2[i2])) - i2++; - if (i1 < s1 || i2 < s2) - return 0; - return 1; - } + while (i1 < s1 && i2 < s2 && l1[i1++] == l2[i2++]) + ; /* keep going */ + } + + /* + * 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 i1 >= s1 && i2 >= s2; - } else - return s1 == s2 && !memcmp(l1, l2, s1); + return (s2 == i2); + } + return 1; } static unsigned long xdl_hash_record_with_whitespace(char const **data, @@ -240,20 +244,22 @@ static unsigned long xdl_hash_record_with_whitespace(char const **data, char const *ptr = *data; for (; ptr < top && *ptr != '\n'; ptr++) { - if (isspace(*ptr)) { + if (XDL_ISSPACE(*ptr)) { const char *ptr2 = ptr; - while (ptr + 1 < top && isspace(ptr[1]) + 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 - && ptr[1] != '\n') { + && !at_eol) { ha += (ha << 5); ha ^= (unsigned long) ' '; } else if (flags & XDF_IGNORE_WHITESPACE_AT_EOL - && ptr[1] != '\n') { + && !at_eol) { while (ptr2 != ptr + 1) { ha += (ha << 5); ha ^= (unsigned long) *ptr2; @@ -380,3 +386,34 @@ int xdl_emit_hunk_hdr(long s1, long c1, long s2, long c2, return 0; } + +int xdl_fall_back_diff(xdfenv_t *diff_env, xpparam_t const *xpp, + int line1, int count1, int line2, int count2) +{ + /* + * This probably does not work outside Git, since + * we have a very simple mmfile structure. + * + * Note: ideally, we would reuse the prepared environment, but + * the libxdiff interface does not (yet) allow for diffing only + * ranges of lines instead of the whole files. + */ + mmfile_t subfile1, subfile2; + xdfenv_t env; + + subfile1.ptr = (char *)diff_env->xdf1.recs[line1 - 1]->ptr; + subfile1.size = diff_env->xdf1.recs[line1 + count1 - 2]->ptr + + diff_env->xdf1.recs[line1 + count1 - 2]->size - subfile1.ptr; + subfile2.ptr = (char *)diff_env->xdf2.recs[line2 - 1]->ptr; + subfile2.size = diff_env->xdf2.recs[line2 + count2 - 2]->ptr + + diff_env->xdf2.recs[line2 + count2 - 2]->size - subfile2.ptr; + if (xdl_do_diff(&subfile1, &subfile2, xpp, &env) < 0) + return -1; + + memcpy(diff_env->xdf1.rchg + line1 - 1, env.xdf1.rchg, count1); + memcpy(diff_env->xdf2.rchg + line2 - 1, env.xdf2.rchg, count2); + + xdl_free_env(&env); + + return 0; +}