now really fix once and for all the #-style comments.

also remove some duplicated code in <?, <%, <%= handlers. this also has the side-effect of producing better bytecodes in some special cases

diff --git a/Zend/zend_language_scanner.l b/Zend/zend_language_scanner.l
index 1169c0d169db44577b7b9d26fe8bcb7d648d3661..39f2c5b30cf2ff64806342c5c41c74e85f95cb02 100644 (file)
--- a/Zend/zend_language_scanner.l
+++ b/Zend/zend_language_scanner.l
@@ -832,6 +832,25 @@ yymore_restart:
                return 0;
        }
 
+       /* ignore first line when it's started with a # */
+       if (YYCURSOR == SCNG(yy_start) && *YYCURSOR == '#') {
+               while (++YYCURSOR < YYLIMIT) {
+                       if (*YYCURSOR == '\n') {
+                               ++YYCURSOR;
+                               goto restart;
+                       }
+
+                       if (*YYCURSOR == '\r') {
+                               if (++YYCURSOR < YYLIMIT && *YYCURSOR == '\n') { /* match \r\n as single newline */
+                                       ++YYCURSOR;
+                               }
+                               goto restart;
+                       }
+               }
+
+               return 0; /* EOF */
+       }
+
 /*!re2c
 re2c:yyfill:check = 0;
 LNUM   [0-9]+
@@ -1549,10 +1568,7 @@ NOWDOC_CHARS             ({NEWLINE}*(([^a-zA-Z_\x7f-\xff\n\r][^\n\r]*)|({LABEL}[^a-zA-Z0-9_
                BEGIN(ST_IN_SCRIPTING);
                return T_OPEN_TAG_WITH_ECHO;
        } else {
-               zendlval->value.str.val = (char *) estrndup(yytext, yyleng);
-               zendlval->value.str.len = yyleng;
-               zendlval->type = IS_STRING;
-               return T_INLINE_HTML;
+               goto inline_char_handler;
        }
 }
 
@@ -1565,10 +1581,7 @@ NOWDOC_CHARS             ({NEWLINE}*(([^a-zA-Z_\x7f-\xff\n\r][^\n\r]*)|({LABEL}[^a-zA-Z0-9_
                BEGIN(ST_IN_SCRIPTING);
                return T_OPEN_TAG_WITH_ECHO;
        } else {
-               zendlval->value.str.val = (char *) estrndup(yytext, yyleng);
-               zendlval->value.str.len = yyleng;
-               zendlval->type = IS_STRING;
-               return T_INLINE_HTML;
+               goto inline_char_handler;
        }
 }
 
@@ -1581,10 +1594,7 @@ NOWDOC_CHARS             ({NEWLINE}*(([^a-zA-Z_\x7f-\xff\n\r][^\n\r]*)|({LABEL}[^a-zA-Z0-9_
                BEGIN(ST_IN_SCRIPTING);
                return T_OPEN_TAG;
        } else {
-               zendlval->value.str.val = (char *) estrndup(yytext, yyleng);
-               zendlval->value.str.len = yyleng;
-               zendlval->type = IS_STRING;
-               return T_INLINE_HTML;
+               goto inline_char_handler;
        }
 }
 
@@ -1600,7 +1610,6 @@ NOWDOC_CHARS              ({NEWLINE}*(([^a-zA-Z_\x7f-\xff\n\r][^\n\r]*)|({LABEL}[^a-zA-Z0-9_
 
 
 <INITIAL>"<?" {
-       HANDLE_NEWLINES(yytext, yyleng);
        if (CG(short_tags)) {
                zendlval->value.str.val = yytext; /* no copying - intentional */
                zendlval->value.str.len = yyleng;
@@ -1608,19 +1617,6 @@ NOWDOC_CHARS             ({NEWLINE}*(([^a-zA-Z_\x7f-\xff\n\r][^\n\r]*)|({LABEL}[^a-zA-Z0-9_
                BEGIN(ST_IN_SCRIPTING);
                return T_OPEN_TAG;
        } else {
-               zendlval->value.str.val = (char *) estrndup(yytext, yyleng);
-               zendlval->value.str.len = yyleng;
-               zendlval->type = IS_STRING;
-               return T_INLINE_HTML;
-       }
-}
-
-<INITIAL>"#".+ {NEWLINE} {
-       if ((YYCTYPE*)yytext == SCNG(yy_start)) {
-               /* ignore first line when it's started with a # */
-               goto restart;
-       } else {
-               YYCURSOR = yytext+1;
                goto inline_char_handler;
        }
 }
@@ -1640,8 +1636,8 @@ inline_char_handler:
                } else {
                        YYCURSOR = ptr + 1;
 
-                       /* if it can be an opening tag, stop */
-                       if (YYCURSOR < YYLIMIT && (*YYCURSOR == '?' || *YYCURSOR == '%')) {
+                       /* stop if it may be an opening tag (<?, <%, <script>). this condition is not optimal though */
+                       if (YYCURSOR < YYLIMIT && (*YYCURSOR == '?' || *YYCURSOR == '%' || *YYCURSOR == 's')) {
                                --YYCURSOR;
                                yyleng = YYCURSOR - SCNG(yy_text);
                                break;