From 164b85a6f94748611dec7bf21852eea5ccb1a49b Mon Sep 17 00:00:00 2001
From: hyung-hwan <hyunghwan.chung@gmail.com>
Date: Sat, 19 Jan 2013 16:21:32 +0000
Subject: [PATCH] changed the number of maximum digits after \x in an awk
 string

---
 qse/doc/page/awk-lang.md | 59 ++++++++++++++++++++++++++++------------
 qse/lib/awk/parse.c      | 17 ++++++------
 2 files changed, 50 insertions(+), 26 deletions(-)

diff --git a/qse/doc/page/awk-lang.md b/qse/doc/page/awk-lang.md
index 5c78276b..7db3f742 100644
--- a/qse/doc/page/awk-lang.md
+++ b/qse/doc/page/awk-lang.md
@@ -13,9 +13,9 @@ tranforms them to an internal form for execution.
 
 An QSEAWK program can be composed of the following elements at the top level.
 
- - pattern-action blocks
  - *BEGIN* blocks
  - *END* blocks
+ - pattern-action blocks
  - user-defined functions
  - comments
  - \@global variables
@@ -107,17 +107,17 @@ point with a preceeding number.
     34.56e # 34.56 
     34.56E3 
 
-An integer can be prefixed with 0x, 0, 0b for a hexa-decimal number, an octal number,
-and a binary number respectively. For a hexa-decimal number, letters from A to F
-can form a number case-insenstively in addition to numeric digits.
+An integer can be prefixed with 0x, 0, 0b for a hexa-decimal number, an octal 
+number, and a binary number respectively. For a hexa-decimal number, letters 
+from A to F can form a number case-insenstively in addition to numeric digits.
 
     0xA1   # 161
     0xB0b0 # 45232
     020    # 16
     0b101  # 5
 
-If the prefix is not followed by any numeric digits, it is still a valid token and
-represents the value of 0.
+If the prefix is not followed by any numeric digits, it is still a valid token 
+and represents the value of 0.
 
     0x # 0x0 but not desirable.
     0b # 0b0 but not desirable.
@@ -127,21 +127,44 @@ represents the value of 0.
 A string is enclosed in a pair of double quotes or single quotes.
 
 A character in a string encosed in the double-quotes, when preceded with 
-a back-slash, changes the meaning.
+a back-slash, changes the meaning. 
 
- - \\
- - \a
- - \b
- - \uXXXX
- - \UXXXXXXXX
+ - \\a - alert
+ - \\b - backspace
+ - \\f - formfeed
+ - \\n - newline
+ - \\r - carriage return
+ - \\t - horizontal tab
+ - \\v - vertical tab
+ - \\\\ - backslash
+ - \\" - double quote
 
-You can use \\u and \\U in a string to specify a character by unicode if  
-[Character Type](@ref installation) chosen for building is the wide character
-type.
+You can specify a character with an octal number or a hexadecimal number.
+The actual value can range between 0 and 255 inclusive.
 
-    BEGIN { 
-        print "\uC720\uB2C8\uCF54\uB4DC \U00007D71\U00004E00\U000078BC"; 
-    }
+ - \\OOO - O is an octal digit.  
+ - \\xXX - X is a hexadecimal digit. 
+
+In the octal sequence, you can specify up to 3 octal digits after \\; In the 
+hexadecimal sequence, you can specify as many hexadecimal digits as possible 
+after \\x.  
+
+If the number doesn't fit in the range that the default character type 
+can represent, the character generated from the sequence is undefined.
+
+You can use \\u and \\U in a string to specify a character by a Unicode code 
+point if  [Character Type](@ref installation) chosen for building is the 
+wide character type.
+
+ - \\uXXXX - X is a hexadecimal digit.
+ - \\UXXXXXXXX - X is a hexadecimal digit.
+
+
+~~~~~{.awk}
+ BEGIN { 
+   print "\uC720\uB2C8\uCF54\uB4DC \U00007D71\U00004E00\U000078BC"; 
+ }
+~~~~~
 
 This program should print 유니코드 統一碼.
 
diff --git a/qse/lib/awk/parse.c b/qse/lib/awk/parse.c
index bf668d7d..1f4f16da 100644
--- a/qse/lib/awk/parse.c
+++ b/qse/lib/awk/parse.c
@@ -5415,11 +5415,11 @@ static int get_number (qse_awk_t* awk, qse_awk_tok_t* tok)
 static int get_string (
 	qse_awk_t* awk, qse_char_t end_char, 
 	qse_char_t esc_char, int keep_esc_char,
-	int preescaped, qse_awk_tok_t* tok)
+	qse_size_t preescaped, qse_awk_tok_t* tok)
 {
 	qse_cint_t c;
-	int escaped = preescaped;
-	int digit_count = 0;
+	qse_size_t escaped = preescaped;
+	qse_size_t digit_count = 0;
 	qse_cint_t c_acc = 0;
 
 	while (1)
@@ -5440,6 +5440,8 @@ static int get_string (
 				digit_count++;
 				if (digit_count >= escaped) 
 				{
+					/* should i limit the max to 0xFF/0377? 
+					 * if (c_acc > 0377) c_acc = 0377;*/
 					ADD_TOKEN_CHAR (awk, tok, c_acc);
 					escaped = 0;
 				}
@@ -5451,7 +5453,7 @@ static int get_string (
 				escaped = 0;
 			}
 		}
-		else if (escaped == 2 || escaped == 4 || escaped == 8)
+		else if (escaped == QSE_TYPE_MAX(qse_size_t) || escaped == 4 || escaped == 8)
 		{
 			if (c >= QSE_T('0') && c <= QSE_T('9'))
 			{
@@ -5490,9 +5492,8 @@ static int get_string (
 			{
 				qse_char_t rc;
 
-				rc = (escaped == 2)? QSE_T('x'):
+				rc = (escaped == QSE_TYPE_MAX(qse_size_t))? QSE_T('x'):
 				     (escaped == 4)? QSE_T('u'): QSE_T('U');
-
 				if (digit_count == 0) 
 					ADD_TOKEN_CHAR (awk, tok, rc);
 				else ADD_TOKEN_CHAR (awk, tok, c_acc);
@@ -5533,12 +5534,12 @@ static int get_string (
 			}
 			else if (c == QSE_T('x')) 
 			{
-				escaped = 2;
+				escaped = QSE_TYPE_MAX(qse_size_t);
 				digit_count = 0;
 				c_acc = 0;
 				continue;
 			}
-		#ifdef QSE_CHAR_IS_WCHAR
+		#if defined(QSE_CHAR_IS_WCHAR)
 			else if (c == QSE_T('u') && QSE_SIZEOF(qse_char_t) >= 2) 
 			{
 				escaped = 4;