From: Ulya Trofimovich <skvadrik@gmail.com>
Date: Tue, 26 May 2015 13:00:01 +0000 (+0100)
Subject: Don't hide the ugly fact that default state in '-f' mode is always state 0.
X-Git-Tag: 0.15~246
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=e315bb4526480d3bd6ffd04baa36144c6ce6de07;p=re2c

Don't hide the ugly fact that default state in '-f' mode is always state 0.

In '-f' mode, state dispatch generation can be triggered in two ways.
Both ways use 're2c::OutputFile::insert_state_goto', which generates
state dispatch only if it hasn't been already generated. The two ways
are:
1. Explicitly, using '/*!getstate:re2c*/'. In this case default state
   must be state 0 because it's hardcoded in the invocation of
   're2c::OutputFile::insert_state_goto' in 'src/parse/scanner_lex.re'.
2. Implicitly, in 're2c::DFA::emit'. In this case default state must
   be state 0 because if 'prolog_label' is not 0, it means that it's
   not the first time 're2c::DFA::emit' is called and state dispatch
   has already been generated.

This commit makes it explicit that re2c always uses state 0.

Note:
    Currently in '-f' mode re2c generates one global dispatch for
    the whole file (the enumeration of yyFillLabel's is also global).
    All re2c blocks share the same state dispatch, so in '-f' mode all
    re2c blocks must reside in the same function and must be parts of
    the same lexer (exception: in '-r' mode re2c generates one state
    dispatch per use block).

    This is clearly an ugly limitation: one is forced put disconnected
    lexers in different files in '-f' mode.

    Now re2c provides conditions as a way to express related blocks,
    so if users used multiple blocks only for unrelated lexers, we
    could safely limit the scope of state dispatch to a single block.
    But conditions can conflict with other re2c features, they are
    a bit broken and I'm pretty sure some users use multiple blocks
    (e.g. I used to do it).

    Thus we cannot just make '-f' generate state dispatch on per-block
    basis (there're some other obstacles: it's not quite clear which
    block '/*!getstate:re2c*/ directive is related to, etc.).

    I leave the situation 'as is' until better times (when lexer-
    parser loop is fixed and the whole code generation model is more
    robust).
---

diff --git a/re2c/bootstrap/scanner_lex.cc b/re2c/bootstrap/scanner_lex.cc
index 311c78ed..469393ad 100644
--- a/re2c/bootstrap/scanner_lex.cc
+++ b/re2c/bootstrap/scanner_lex.cc
@@ -328,7 +328,7 @@ yy50:
 	++YYCURSOR;
 	{
 					tok = pos = cursor;
-					out.insert_state_goto (topIndent, 0);
+					out.insert_state_goto (topIndent);
 					ignore_eoc = true;
 					goto echo;
 				}
diff --git a/re2c/src/codegen/emit_dfa.cc b/re2c/src/codegen/emit_dfa.cc
index a331cc28..cd3acaff 100644
--- a/re2c/src/codegen/emit_dfa.cc
+++ b/re2c/src/codegen/emit_dfa.cc
@@ -102,6 +102,10 @@ void DFA::emit(Output & output, uint32_t& ind, const RegExpMap* specMap, const s
 		s->label = next_label++;
 	}
 
+	if (fFlag)
+	{
+		vUsedLabels.insert(0);
+	}
 	for (s = head; s; s = s->next)
 	{
 		s->go.used_labels ();
@@ -157,7 +161,7 @@ void DFA::emit(Output & output, uint32_t& ind, const RegExpMap* specMap, const s
 	if (bProlog)
 	{
 		genCondTable(o, ind, *specMap);
-		o.insert_state_goto (ind, prolog_label);
+		o.insert_state_goto (ind);
 		if (cFlag && !DFlag)
 		{
 			if (vUsedLabels.count(prolog_label))
diff --git a/re2c/src/codegen/output.cc b/re2c/src/codegen/output.cc
index 9d50ad8c..72a88c90 100644
--- a/re2c/src/codegen/output.cc
+++ b/re2c/src/codegen/output.cc
@@ -51,7 +51,6 @@ OutputFile::OutputFile (const char * fn)
 	: file_name (fn)
 	, file (NULL)
 	, blocks ()
-	, prolog_label (0)
 {
 	new_block ();
 }
@@ -150,12 +149,10 @@ void OutputFile::insert_line_info ()
 	insert_code ();
 }
 
-void OutputFile::insert_state_goto (uint32_t ind, uint32_t start_label)
+void OutputFile::insert_state_goto (uint32_t ind)
 {
 	if (fFlag && !bWroteGetState)
 	{
-		prolog_label = start_label;
-		vUsedLabels.insert (start_label);
 		blocks.back ()->fragments.push_back (new OutputFragment (OutputFragment::STATE_GOTO, ind));
 		insert_code ();
 		bWroteGetState = true;
@@ -226,7 +223,7 @@ void OutputFile::emit
 						output_line_info (f.stream, line_count + 1, file_name);
 						break;
 					case OutputFragment::STATE_GOTO:
-						output_state_goto (f.stream, f.indent, prolog_label);
+						output_state_goto (f.stream, f.indent, 0);
 						break;
 					case OutputFragment::TYPES:
 						output_types (f.stream, f.indent, types);
diff --git a/re2c/src/codegen/output.h b/re2c/src/codegen/output.h
index 860bae25..fae5dea4 100644
--- a/re2c/src/codegen/output.h
+++ b/re2c/src/codegen/output.h
@@ -69,7 +69,7 @@ struct OutputFile
 	friend OutputFile & operator << (OutputFile & o, const char * s);
 
 	void insert_line_info ();
-	void insert_state_goto (uint32_t ind, uint32_t start_label);
+	void insert_state_goto (uint32_t ind);
 	void insert_types ();
 	void insert_yyaccept_init (uint32_t ind);
 	void insert_yyaccept_selector (uint32_t ind, uint32_t selector);
@@ -84,7 +84,6 @@ private:
 	const char * file_name;
 	FILE * file;
 	std::vector<OutputBlock *> blocks;
-	uint32_t prolog_label;
 
 	std::ostream & stream ();
 	void insert_code ();
diff --git a/re2c/src/parse/scanner_lex.re b/re2c/src/parse/scanner_lex.re
index 8a5c24c1..6ddc5082 100644
--- a/re2c/src/parse/scanner_lex.re
+++ b/re2c/src/parse/scanner_lex.re
@@ -112,7 +112,7 @@ echo:
 				}
 	"/*!getstate:re2c" {
 					tok = pos = cursor;
-					out.insert_state_goto (topIndent, 0);
+					out.insert_state_goto (topIndent);
 					ignore_eoc = true;
 					goto echo;
 				}