Added automatic EOI check

README.md

@@ -32,6 +32,8 @@ The PEG syntax is well described on page 2 in the [document](http://www.brynosau
   * `exp⇑label` or `exp^label` (Syntax sugar for `(exp / %recover(label))`)
   * `label { message "..." }` (Error message instruction)
 
+'End of Input' check will be done as default. In order to disable the check, please call `disable_eoi_check`.
+
 This library supports the linear-time parsing known as the [*Packrat*](http://pdos.csail.mit.edu/~baford/packrat/thesis/thesis.pdf) parsing.
 
   IMPORTANT NOTE for some Linux distributions such as Ubuntu and CentOS: Need `-pthread` option when linking. See [#23](https://github.com/yhirose/cpp-peglib/issues/23#issuecomment-261126127), [#46](https://github.com/yhirose/cpp-peglib/issues/46#issuecomment-417870473) and [#62](https://github.com/yhirose/cpp-peglib/issues/62#issuecomment-492032680).

peglib.h

@@ -2358,6 +2358,8 @@ public:
   std::string error_message;
   bool no_ast_opt = false;
 
+  bool eoi_check = true;
+
 private:
   friend class Reference;
   friend class ParserGenerator;
@@ -2409,12 +2411,14 @@ private:
     auto ret = success(len);
     if (ret) {
       i += len;
-      if (i < n) {
+      if (eoi_check) {
-        if (c.error_info.error_pos - c.s < s + i - c.s) {
+        if (i < n) {
-          c.error_info.message_pos = s + i;
+          if (c.error_info.error_pos - c.s < s + i - c.s) {
-          c.error_info.message = "expected end of input";
+            c.error_info.message_pos = s + i;
+            c.error_info.message = "expected end of input";
+          }
+          ret = false;
         }
-        ret = false;
       }
     }
     return Result{ret, c.recovered, i, c.error_info};
@@ -4410,6 +4414,13 @@ public:
     return rules;
   }
 
+  void disable_eoi_check() {
+    if (grammar_ != nullptr) {
+      auto &rule = (*grammar_)[start_];
+      rule.eoi_check = false;
+    }
+  }
+
   void enable_packrat_parsing() {
     if (grammar_ != nullptr) {
       auto &rule = (*grammar_)[start_];

test/test1.cc

@@ -977,6 +977,17 @@ TEST(GeneralTest, ParentReferencesShouldNotBeExpired) {
 }
 
 TEST(GeneralTest, EndOfInputTest) {
+  auto parser = peg::parser(R"(
+    S <- '[[' (!']]' .)* ']]' !.
+	)");
+
+  parser.disable_eoi_check();
+
+  auto ret = parser.parse("[[]]]");
+  EXPECT_FALSE(ret);
+}
+
+TEST(GeneralTest, DefaultEndOfInputTest) {
   auto parser = peg::parser(R"(
     S <- '[[' (!']]' .)* ']]'
 	)");
@@ -987,10 +998,12 @@ TEST(GeneralTest, EndOfInputTest) {
 
 TEST(GeneralTest, DisableEndOfInputCheckTest) {
   auto parser = peg::parser(R"(
-    S <- '[[' (!']]' .)* ']]' !.
+    S <- '[[' (!']]' .)* ']]'
 	)");
 
+  parser.disable_eoi_check();
+
   auto ret = parser.parse("[[]]]");
-  EXPECT_FALSE(ret);
+  EXPECT_TRUE(ret);
 }
 

test/test2.cc

@@ -1228,7 +1228,7 @@ TEST(DicTest, Dictionary_invalid) {
 
 TEST(ErrorTest, Default_error_handling_1) {
   parser pg(R"(
-    S <- '@' A B !.
+    S <- '@' A B
     A <- < [a-z]+ >
     B <- 'hello' | 'world'
     %whitespace <- [ ]*
@@ -1253,7 +1253,7 @@ TEST(ErrorTest, Default_error_handling_1) {
 
 TEST(ErrorTest, Default_error_handling_2) {
   parser pg(R"(
-    S <- '@' A B !.
+    S <- '@' A B
     A <- < [a-z]+ >
     B <- 'hello' / 'world'
     %whitespace <- ' '*
@@ -1279,7 +1279,7 @@ TEST(ErrorTest, Default_error_handling_2) {
 TEST(ErrorTest, Default_error_handling_fiblang) {
   parser pg(R"(
     # Syntax
-    START             ← STATEMENTS !.
+    START             ← STATEMENTS
     STATEMENTS        ← (DEFINITION / EXPRESSION)*
     DEFINITION        ← 'def' ↑ Identifier '(' Identifier ')' EXPRESSION
     EXPRESSION        ← TERNARY
@@ -1326,7 +1326,7 @@ for n frm 1 to 30
 
 TEST(ErrorTest, Error_recovery_1) {
   parser pg(R"(
-START      <- __? SECTION* !.
+START      <- __? SECTION*
 
 SECTION    <- HEADER __ ENTRIES __?
 
@@ -1490,29 +1490,13 @@ TEST(ErrorTest, Error_recovery_2) {
   )",
                ast));
 
-  ast = pg.optimize_ast(ast);
+  EXPECT_FALSE(ast);
-
-  EXPECT_EQ(R"(+ START
-  - ENTRY/0[NUM] (000)
-  - ENTRY/0[NUM] (111)
-  + ENTRY
-    + ITEM/2
-    + ITEM/2
-    - ITEM/0[WORD] ("bbb")
-    + ITEM/2
-  + ENTRY
-    + ITEM/2
-    - ITEM/1[NUM] (444)
-    - ITEM/1[NUM] (555)
-    + ITEM/2
-)",
-            ast_to_s(ast));
 }
 
 TEST(ErrorTest, Error_recovery_3) {
   parser pg(R"~(
 # Grammar
-START      <- __? SECTION* !.
+START      <- __? SECTION*
 
 SECTION    <- HEADER __ ENTRIES __?
 
@@ -1723,7 +1707,7 @@ sss | ttt
 
 TEST(ErrorTest, Error_recovery_Java) {
   parser pg(R"(
-Prog       ← PUBLIC CLASS NAME LCUR PUBLIC STATIC VOID MAIN LPAR STRING LBRA RBRA NAME RPAR BlockStmt RCUR !.
+Prog       ← PUBLIC CLASS NAME LCUR PUBLIC STATIC VOID MAIN LPAR STRING LBRA RBRA NAME RPAR BlockStmt RCUR
 BlockStmt  ← LCUR (Stmt)* RCUR^rcblk
 Stmt       ← IfStmt / WhileStmt / PrintStmt / DecStmt / AssignStmt / BlockStmt
 IfStmt     ← IF LPAR Exp RPAR Stmt (ELSE Stmt)?