From: Ulya Trofimovich <skvadrik@gmail.com>
Date: Tue, 11 Aug 2015 10:12:32 +0000 (+0100)
Subject: Simplified pretty-printing individual characters.
X-Git-Tag: 0.15~134
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=a0fe9a05799ffe4d0ac8b56ec602ebfe213a0da7;p=re2c

Simplified pretty-printing individual characters.
---

diff --git a/re2c/src/codegen/go_emit.cc b/re2c/src/codegen/go_emit.cc
index c196e646..542108fd 100644
--- a/re2c/src/codegen/go_emit.cc
+++ b/re2c/src/codegen/go_emit.cc
@@ -71,7 +71,7 @@ void Case::emit (OutputFile & o, uint32_t ind)
 			if (dFlag && encoding.is (Enc::EBCDIC))
 			{
 				const uint32_t c = encoding.decodeUnsafe (b);
-				if (isprint (c))
+				if (is_print (c))
 					o << " /* " << static_cast<char> (c) << " */";
 			}
 			bool last_case = i == ranges.size () - 1 && b == ranges[i].second - 1;
diff --git a/re2c/src/codegen/print.cc b/re2c/src/codegen/print.cc
index 2ab73d55..58d06345 100644
--- a/re2c/src/codegen/print.cc
+++ b/re2c/src/codegen/print.cc
@@ -6,6 +6,27 @@
 namespace re2c
 {
 
+bool is_print (uint32_t c)
+{
+	return c >= 0x20 && c < 0x7F;
+}
+
+bool is_space (uint32_t c)
+{
+	switch (c)
+	{
+		case '\t':
+		case '\f':
+		case '\v':
+		case '\n':
+		case '\r':
+		case ' ':
+			return true;
+		default:
+			return false;
+	}
+}
+
 char hexCh(uint32_t c)
 {
 	static const char * sHex = "0123456789ABCDEF";
@@ -14,7 +35,8 @@ char hexCh(uint32_t c)
 
 void prtChOrHex(std::ostream& o, uint32_t c)
 {
-	if (!encoding.is(Enc::EBCDIC) && (c < 256u) && (isprint(c) || isspace(c)))
+	if (!encoding.is (Enc::EBCDIC)
+		&& (is_print (c) || is_space (c)))
 	{
 		o << '\'';
 		prtCh(o, c);
@@ -28,34 +50,22 @@ void prtChOrHex(std::ostream& o, uint32_t c)
 
 void prtHex(std::ostream& o, uint32_t c)
 {
-	int oc = (int)(c);
-
-	if (encoding.szCodeUnit() == 4)
-	{
-		o << "0x"
-		  << hexCh(oc >> 28)
-		  << hexCh(oc >> 24)
-		  << hexCh(oc >> 20)
-		  << hexCh(oc >> 16)
-		  << hexCh(oc >> 12)
-		  << hexCh(oc >>  8)
-		  << hexCh(oc >>  4)
-		  << hexCh(oc);
-	}
-	else if (encoding.szCodeUnit() == 2)
+	o << "0x";
+	const uint32_t cunit_size = encoding.szCodeUnit ();
+	if (cunit_size >= 4)
 	{
-		o << "0x"
-		  << hexCh(oc >> 12)
-		  << hexCh(oc >>  8)
-		  << hexCh(oc >>  4)
-		  << hexCh(oc);
+		o << hexCh (c >> 28u)
+			<< hexCh (c >> 24u)
+			<< hexCh (c >> 20u)
+			<< hexCh (c >> 16u);
 	}
-	else
+	if (cunit_size >= 2)
 	{
-		o << "0x"
-		  << hexCh(oc >>  4) 
-		  << hexCh(oc);
+		o << hexCh (c >> 12u)
+			<< hexCh (c >> 8u);
 	}
+	o << hexCh (c >> 4u)
+		<< hexCh (c);
 }
 
 void prtCh(std::ostream& o, uint32_t c)
@@ -110,7 +120,9 @@ void prtCh(std::ostream& o, uint32_t c)
 
 void prtChOrHexForSpan(std::ostream& o, uint32_t c)
 {
-	if (!encoding.is(Enc::EBCDIC) && (c < 256u) && isprint(c) && (c != ']'))
+	if (!encoding.is(Enc::EBCDIC)
+		&& is_print (c)
+		&& (c != ']'))
 	{
 		prtCh(o, c);
 	}
diff --git a/re2c/src/codegen/print.h b/re2c/src/codegen/print.h
index 59d97fdd..045796d1 100644
--- a/re2c/src/codegen/print.h
+++ b/re2c/src/codegen/print.h
@@ -8,6 +8,8 @@
 namespace re2c
 {
 
+bool is_print (uint32_t c);
+bool is_space (uint32_t c);
 char hexCh(uint32_t c);
 void prtCh(std::ostream&, uint32_t);
 void prtHex(std::ostream&, uint32_t);