[Feature #13712] String#start_with? supports regexp

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@60234 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

NEWS

@@ -108,6 +108,7 @@ with all sufficient information, see the ChangeLog file or Redmine
   * String#delete_suffix! is added to remove suffix destructively [Feature #13665]
   * String#each_grapheme_cluster and String#grapheme_clusters is added to
     enumerate grapheme clusters [Feature #13780]
+  * String#start_with? supports regexp [Feature #13712]
 
 * Regexp/String: Updated Unicode version from 9.0.0 to 10.0.0 [Feature #13685]
 

internal.h

@@ -1570,6 +1570,7 @@ VALUE rb_reg_compile(VALUE str, int options, const char *sourcefile, int sourcel
 VALUE rb_reg_check_preprocess(VALUE);
 long rb_reg_search0(VALUE, VALUE, long, int, int);
 VALUE rb_reg_match_p(VALUE re, VALUE str, long pos);
+bool rb_reg_start_with_p(VALUE re, VALUE str);
 void rb_backref_set_string(VALUE string, long pos, long len);
 int rb_match_count(VALUE match);
 int rb_match_nth_defined(int nth, VALUE match);

re.c

@@ -1580,6 +1580,83 @@ rb_reg_search(VALUE re, VALUE str, long pos, int reverse)
     return rb_reg_search0(re, str, pos, reverse, 1);
 }
 
+bool
+rb_reg_start_with_p(VALUE re, VALUE str)
+{
+    long result;
+    VALUE match;
+    struct re_registers regi, *regs = &regi;
+    regex_t *reg;
+    int tmpreg;
+    onig_errmsg_buffer err = "";
+
+    reg = rb_reg_prepare_re0(re, str, err);
+    tmpreg = reg != RREGEXP_PTR(re);
+    if (!tmpreg) RREGEXP(re)->usecnt++;
+
+    match = rb_backref_get();
+    if (!NIL_P(match)) {
+	if (FL_TEST(match, MATCH_BUSY)) {
+	    match = Qnil;
+	}
+	else {
+	    regs = RMATCH_REGS(match);
+	}
+    }
+    if (NIL_P(match)) {
+	MEMZERO(regs, struct re_registers, 1);
+    }
+    result = onig_match(reg,
+	    (UChar*)(RSTRING_PTR(str)),
+	    ((UChar*)(RSTRING_PTR(str)) + RSTRING_LEN(str)),
+	    (UChar*)(RSTRING_PTR(str)),
+	    regs, ONIG_OPTION_NONE);
+    if (!tmpreg) RREGEXP(re)->usecnt--;
+    if (tmpreg) {
+	if (RREGEXP(re)->usecnt) {
+	    onig_free(reg);
+	}
+	else {
+	    onig_free(RREGEXP_PTR(re));
+	    RREGEXP_PTR(re) = reg;
+	}
+    }
+    if (result < 0) {
+	if (regs == &regi)
+	    onig_region_free(regs, 0);
+	if (result == ONIG_MISMATCH) {
+	    rb_backref_set(Qnil);
+	    return false;
+	}
+	else {
+	    onig_error_code_to_str((UChar*)err, (int)result);
+	    rb_reg_raise(RREGEXP_SRC_PTR(re), RREGEXP_SRC_LEN(re), err, re);
+	}
+    }
+
+    if (NIL_P(match)) {
+	int err;
+	match = match_alloc(rb_cMatch);
+	err = rb_reg_region_copy(RMATCH_REGS(match), regs);
+	onig_region_free(regs, 0);
+	if (err) rb_memerror();
+    }
+    else {
+	FL_UNSET(match, FL_TAINT);
+    }
+
+    RMATCH(match)->str = rb_str_new4(str);
+    OBJ_INFECT(match, str);
+
+    RMATCH(match)->regexp = re;
+    RMATCH(match)->rmatch->char_offset_updated = 0;
+    rb_backref_set(match);
+
+    OBJ_INFECT(match, re);
+
+    return true;
+}
+
 VALUE
 rb_reg_nth_defined(int nth, VALUE match)
 {

string.c

@@ -9219,11 +9219,20 @@ rb_str_start_with(int argc, VALUE *argv, VALUE str)
 
     for (i=0; i<argc; i++) {
 	VALUE tmp = argv[i];
-	StringValue(tmp);
+	switch (TYPE(tmp)) {
-	rb_enc_check(str, tmp);
+	  case T_REGEXP:
-	if (RSTRING_LEN(str) < RSTRING_LEN(tmp)) continue;
+	    {
-	if (memcmp(RSTRING_PTR(str), RSTRING_PTR(tmp), RSTRING_LEN(tmp)) == 0)
+		bool r = rb_reg_start_with_p(tmp, str);
-	    return Qtrue;
+		if (r) return Qtrue;
+	    }
+	    break;
+	  default:
+	    StringValue(tmp);
+	    rb_enc_check(str, tmp);
+	    if (RSTRING_LEN(str) < RSTRING_LEN(tmp)) continue;
+	    if (memcmp(RSTRING_PTR(str), RSTRING_PTR(tmp), RSTRING_LEN(tmp)) == 0)
+		return Qtrue;
+	}
     }
     return Qfalse;
 }

test/ruby/test_string.rb

@@ -1723,6 +1723,11 @@ CODE
 
     bug5536 = '[ruby-core:40623]'
     assert_raise(TypeError, bug5536) {S("str").start_with? :not_convertible_to_string}
+
+    assert_equal(true, "hello".start_with?(/hel/))
+    assert_equal("hel", $&)
+    assert_equal(false, "hello".start_with?(/el/))
+    assert_nil($&)
   end
 
   def test_strip