/*
* Diff related functions
*/
+static XBT_INLINE int diff_get(xbt_matrix_t C, int i, int j)
+{
+ return (i == -1 || j == -1) ? 0 : xbt_matrix_get_as(C, i, j, int);
+}
+
static xbt_matrix_t diff_build_LCS(xbt_dynar_t da, xbt_dynar_t db)
{
xbt_matrix_t C =
xbt_matrix_new(xbt_dynar_length(da), xbt_dynar_length(db),
sizeof(int), NULL);
- unsigned long i, j;
+ int i, j;
/* Compute the LCS */
/*
- C = array(0..m, 0..n)
- for i := 0..m
- C[i,0] = 0
- for j := 1..n
- C[0,j] = 0
- for i := 1..m
- for j := 1..n
- if X[i] = Y[j]
- C[i,j] := C[i-1,j-1] + 1
- else:
- C[i,j] := max(C[i,j-1], C[i-1,j])
- return C[m,n]
+ function LCSLength(X[1..m], Y[1..n])
+ C = array(0..m, 0..n)
+ for i := 0..m
+ C[i,0] = 0
+ for j := 1..n
+ C[0,j] = 0
+ for i := 1..m
+ for j := 1..n
+ if X[i] = Y[j]
+ C[i,j] := C[i-1,j-1] + 1
+ else:
+ C[i,j] := max(C[i,j-1], C[i-1,j])
+ return C[m,n]
*/
- if (xbt_dynar_length(db) != 0)
- for (i = 0; i < xbt_dynar_length(da); i++)
- *((int *) xbt_matrix_get_ptr(C, i, 0)) = 0;
-
- if (xbt_dynar_length(da) != 0)
- for (j = 0; j < xbt_dynar_length(db); j++)
- *((int *) xbt_matrix_get_ptr(C, 0, j)) = 0;
-
- for (i = 1; i < xbt_dynar_length(da); i++)
- for (j = 1; j < xbt_dynar_length(db); j++) {
-
- if (!strcmp
- (xbt_dynar_get_as(da, i, char *),
- xbt_dynar_get_as(db, j, char *)))
- *((int *) xbt_matrix_get_ptr(C, i, j)) =
- xbt_matrix_get_as(C, i - 1, j - 1, int) + 1;
+ for (i = 0; i < (int)xbt_dynar_length(da); i++)
+ for (j = 0; j < (int)xbt_dynar_length(db); j++) {
+
+ if (!strcmp(xbt_dynar_get_as(da, i, char *),
+ xbt_dynar_get_as(db, j, char *)))
+ *((int *) xbt_matrix_get_ptr(C, i, j)) = diff_get(C, i - 1, j - 1) + 1;
else
- *((int *) xbt_matrix_get_ptr(C, i, j)) =
- max(xbt_matrix_get_as(C, i, j - 1, int),
- xbt_matrix_get_as(C, i - 1, j, int));
+ *((int *) xbt_matrix_get_ptr(C, i, j)) = max(diff_get(C, i, j - 1),
+ diff_get(C, i - 1, j));
}
return C;
}
char *topush;
/* Construct the diff
function printDiff(C[0..m,0..n], X[1..m], Y[1..n], i, j)
- if i > 0 and j > 0 and X[i] = Y[j]
- printDiff(C, X, Y, i-1, j-1)
- print " " + X[i]
- else
- if j > 0 and (i = 0 or C[i,j-1] >= C[i-1,j])
- printDiff(C, X, Y, i, j-1)
- print "+ " + Y[j]
- else if i > 0 and (j = 0 or C[i,j-1] < C[i-1,j])
- printDiff(C, X, Y, i-1, j)
- print "- " + X[i]
+ if i > 0 and j > 0 and X[i] = Y[j]
+ printDiff(C, X, Y, i-1, j-1)
+ print " " + X[i]
+ else
+ if j > 0 and (i = 0 or C[i,j-1] >= C[i-1,j])
+ printDiff(C, X, Y, i, j-1)
+ print "+ " + Y[j]
+ else if i > 0 and (j = 0 or C[i,j-1] < C[i-1,j])
+ printDiff(C, X, Y, i-1, j)
+ print "- " + X[i]
*/
if (i >= 0 && j >= 0 && !strcmp(xbt_dynar_get_as(da, i, char *),
topush = bprintf(" %s", xbt_dynar_get_as(da, i, char *));
xbt_dynar_push(res, &topush);
} else if (j >= 0 &&
- (i <= 0 || j == 0
- || xbt_matrix_get_as(C, i, j - 1,
- int) >= xbt_matrix_get_as(C, i - 1, j,
- int))) {
+ (i == -1 || diff_get(C, i, j - 1) >= diff_get(C, i - 1, j))) {
diff_build_diff(res, C, da, db, i, j - 1);
topush = bprintf("+ %s", xbt_dynar_get_as(db, j, char *));
xbt_dynar_push(res, &topush);
} else if (i >= 0 &&
- (j <= 0
- || xbt_matrix_get_as(C, i, j - 1, int) < xbt_matrix_get_as(C,
- i
- -
- 1,
- j,
- int)))
- {
+ (j == -1 || diff_get(C, i, j - 1) < diff_get(C, i - 1, j))) {
diff_build_diff(res, C, da, db, i - 1, j);
topush = bprintf("- %s", xbt_dynar_get_as(da, i, char *));
xbt_dynar_push(res, &topush);
- } else if (i <= 0 && j <= 0) {
- return;
- } else {
- THROWF(arg_error, 0, "Invalid values: i=%d, j=%d", i, j);
}
-
}
/** @brief Compute the unified diff of two strings */
{
xbt_dynar_t da = xbt_str_split(a, "\n");
xbt_dynar_t db = xbt_str_split(b, "\n");
+ xbt_matrix_t C;
+ xbt_dynar_t diff;
+ char *res;
+ size_t len;
- xbt_matrix_t C = diff_build_LCS(da, db);
- xbt_dynar_t diff = xbt_dynar_new(sizeof(char *), &xbt_free_ref);
- char *res = NULL;
+ /* Clean empty lines at the end of da and db */
+ len = strlen(a);
+ if (len > 0 && a[len - 1] == '\n') {
+ char *str;
+ xbt_dynar_pop(da, &str);
+ free(str);
+ }
+ len = strlen(b);
+ if (len > 0 && b[len - 1] == '\n') {
+ char *str;
+ xbt_dynar_pop(db, &str);
+ free(str);
+ }
+
+ C = diff_build_LCS(da, db);
+ diff = xbt_dynar_new(sizeof(char *), &xbt_free_ref);
diff_build_diff(diff, C, da, db, xbt_dynar_length(da) - 1,
xbt_dynar_length(db) - 1);
- /* Clean empty lines at the end */
- while (xbt_dynar_length(diff) > 0) {
- char *str;
- xbt_dynar_pop(diff, &str);
- if (str[0] == '\0' || !strcmp(str, " ")) {
- free(str);
- } else {
- xbt_dynar_push(diff, &str);
- break;
- }
- }
res = xbt_str_join(diff, "\n");
xbt_dynar_free(&da);
mytest_str("String with no separator in it", "toto", "##", "toto");
mytest_str("Basic test", "toto##tutu", "##", "totoXXXtutu");
}
+
+#define mytest_diff(name, s1, s2, diff) \
+ do { \
+ char *mytest_diff_res; \
+ xbt_test_add(name); \
+ mytest_diff_res = xbt_str_diff(s1, s2); \
+ xbt_test_assert(!strcmp(mytest_diff_res, diff), \
+ "Wrong output:\n--- got:\n%s\n--- expected:\n%s\n---", \
+ mytest_diff_res, diff); \
+ free(mytest_diff_res); \
+ } while (0)
+
+XBT_TEST_UNIT("xbt_str_diff", test_diff, "test the function xbt_str_diff")
+{
+ unsigned i;
+
+ /* Trivial cases */
+ mytest_diff("1 word, no difference", "a", "a", " a");
+ mytest_diff("1 word, different", "a", "A", "- a\n+ A");
+ mytest_diff("1 line, no difference", "a\n", "a\n", " a");
+ mytest_diff("1 line, different", "a\n", "A\n", "- a\n+ A");
+
+ /* Empty strings */
+ mytest_diff("empty strings", "", "", "");
+ mytest_diff("1 word, added", "", "a", "+ a");
+ mytest_diff("1 word, removed", "a", "", "- a");
+ mytest_diff("1 line, added", "", "a\n", "+ a");
+ mytest_diff("1 line, removed", "a\n", "", "- a");
+ mytest_diff("4 lines, all added", "", "a\nb\nc\n", "+ a\n+ b\n+ c");
+ mytest_diff("4 lines, all removed", "a\nb\nc\n", "", "- a\n- b\n- c");
+
+ /* Empty lines */
+ mytest_diff("empty lines", "\n", "\n", " ");
+ mytest_diff("empty line, added", "", "\n", "+ ");
+ mytest_diff("empty line, removed", "\n", "", "- ");
+
+ mytest_diff("empty line added before word", "a", "\na", "+ \n a");
+ mytest_diff("empty line added after word", "a", "a\n\n", " a\n+ ");
+ mytest_diff("empty line removed before word", "\na", "a", "- \n a");
+ mytest_diff("empty line removed after word", "a\n\n", "a", " a\n- ");
+
+ mytest_diff("empty line added before line", "a\n", "\na\n", "+ \n a");
+ mytest_diff("empty line added after line", "a\n", "a\n\n", " a\n+ ");
+ mytest_diff("empty line removed before line", "\na\n", "a\n", "- \n a");
+ mytest_diff("empty line removed after line", "a\n\n", "a\n", " a\n- ");
+
+ mytest_diff("empty line added before 4 lines",
+ "a\nb\nc\nd\n", "\na\nb\nc\nd\n", "+ \n a\n b\n c\n d");
+ mytest_diff("empty line added after 4 lines",
+ "a\nb\nc\nd\n", "a\nb\nc\nd\n\n", " a\n b\n c\n d\n+ ");
+ mytest_diff("empty line removed before 4 lines",
+ "\na\nb\nc\nd\n", "a\nb\nc\nd\n", "- \n a\n b\n c\n d");
+ mytest_diff("empty line removed after 4 lines",
+ "a\nb\nc\nd\n\n", "a\nb\nc\nd\n", " a\n b\n c\n d\n- ");
+
+ /* Missing newline at the end of one of the strings */
+ mytest_diff("1 line, 1 word, no difference", "a\n", "a", " a");
+ mytest_diff("1 word, 1 line, no difference", "a", "a\n", " a");
+ mytest_diff("1 line, 1 word, different", "a\n", "A", "- a\n+ A");
+ mytest_diff("1 word, 1 line, different", "a", "A\n", "- a\n+ A");
+
+ mytest_diff("4 lines, no newline on first",
+ "a\nb\nc\nd", "a\nb\nc\nd\n", " a\n b\n c\n d");
+ mytest_diff("4 lines, no newline on second",
+ "a\nb\nc\nd\n", "a\nb\nc\nd", " a\n b\n c\n d");
+
+ /* Four lines, all combinations of differences */
+ for (i = 0 ; i < (1U << 4) ; i++) {
+ char descr[80];
+ char d2[4 + 1];
+ char s2[4 * 2 + 1];
+ char res[4 * 8 + 1];
+ char *pd = d2;
+ char *ps = s2;
+ char *pr = res;
+ unsigned j = 0;
+ while (j < 4) {
+ unsigned k;
+ for (/* j */ ; j < 4 && !(i & (1U << j)) ; j++) {
+ *pd++ = "abcd"[j];
+ ps += sprintf(ps, "%c\n", "abcd"[j]);
+ pr += sprintf(pr, " %c\n", "abcd"[j]);
+ }
+ for (k = j ; k < 4 && (i & (1U << k)) ; k++) {
+ *pd++ = "ABCD"[k];
+ ps += sprintf(ps, "%c\n", "ABCD"[k]);
+ pr += sprintf(pr, "- %c\n", "abcd"[k]);
+ }
+ for (/* j */ ; j < k ; j++) {
+ pr += sprintf(pr, "+ %c\n", "ABCD"[j]);
+ }
+ }
+ *pd = '\0';
+ *--pr = '\0'; /* strip last '\n' from expected result */
+ sprintf(descr, "compare (abcd) with changed (%s)", d2);
+ mytest_diff(descr, "a\nb\nc\nd\n", s2, res);
+ }
+
+ /* Subsets of four lines, do not test for empty subset */
+ for (i = 1 ; i < (1U << 4) ; i++) {
+ char descr[80];
+ char d2[4 + 1];
+ char s2[4 * 2 + 1];
+ char res[4 * 8 + 1];
+ char *pd = d2;
+ char *ps = s2;
+ char *pr = res;
+ unsigned j = 0;
+ while (j < 4) {
+ for (/* j */ ; j < 4 && (i & (1U << j)) ; j++) {
+ *pd++ = "abcd"[j];
+ ps += sprintf(ps, "%c\n", "abcd"[j]);
+ pr += sprintf(pr, " %c\n", "abcd"[j]);
+ }
+ for (/* j */; j < 4 && !(i & (1U << j)) ; j++) {
+ pr += sprintf(pr, "- %c\n", "abcd"[j]);
+ }
+ }
+ *pd = '\0';
+ *--pr = '\0'; /* strip last '\n' from expected result */
+ sprintf(descr, "compare (abcd) with subset (%s)", d2);
+ mytest_diff(descr, "a\nb\nc\nd\n", s2, res);
+
+ for (pr = res ; *pr != '\0' ; pr++)
+ if (*pr == '-')
+ *pr = '+';
+ sprintf(descr, "compare subset (%s) with (abcd)", d2);
+ mytest_diff(descr, s2, "a\nb\nc\nd\n", res);
+ }
+}
+
#endif /* SIMGRID_TEST */