From bd7e5c441db498b1c1b576443d15574d0ff1f83d Mon Sep 17 00:00:00 2001
From: "Jon J. C" <juaristi@uni-heidelberg.de>
Date: Wed, 18 Oct 2023 13:16:43 +0200
Subject: [PATCH 1/4] Adapt PEG syntax to the one defined by Bryan Ford on the
 original paper. Breaks arpeggio tests.

---
 src/peg/adql2.1.peg | 40 ++++++++++++++++++++++------------------
 1 file changed, 22 insertions(+), 18 deletions(-)

diff --git a/src/peg/adql2.1.peg b/src/peg/adql2.1.peg
index 171d18a..9172e2c 100644
--- a/src/peg/adql2.1.peg
+++ b/src/peg/adql2.1.peg
@@ -1,9 +1,4 @@
 # Note: in the actual PEG definition comments start with #
-# =========================== Configurables for deployers
-
-# additional prefixes to be added here
-udf_prefix <-
-	'ivo_'
 
 # ============================ The Gramma's root symbol
 
@@ -245,13 +240,13 @@ identifier <-
 	(regular_identifier / delimited_identifier)
 
 delimited_identifier <-
-	'"' ('""' / '[^"]')+ '"'
+	'"' ('""' / !["])+ '"'
 
 regular_identifier <-
 	(!(keyword) letter (letter / digit / '_')*)
 
 character_string_literal <-
-	("'" ("''" / r"[^']")* "'" (Space+ comment _)*)+
+	("'" ("''" / !['])* "'" (Space+ comment _)*)+
 
 fold_function <-
 	('UPPER' / 'LOWER') _
@@ -280,7 +275,7 @@ geometry_function <-
 	/ extract_coord_sys
 
 bitwise_op <-
-	'&' / '|' / '^'
+	[&|^]
 
 bitwise_expression <-
 	'~' numeric_value_expression
@@ -456,13 +451,13 @@ point <-
 	_ ',' _ coordinates _ ')'
 
 numeric_value_expression <-
-	term (_ ('+' / '-') _ numeric_value_expression)*
+	term (_ [-+] _ numeric_value_expression)*
 
 term <-
-	factor (_ ('*' / '/') _ term)*
+	factor (_ [*/] _ term)*
 
 factor <-
-	('+' / '-')? numeric_primary
+	[-+]? numeric_primary
 
 numeric_value_function <-
 	math_function
@@ -531,7 +526,7 @@ numeric_expression_operand <-
 	numeric_value_expression
 
 numeric_expression_rest <-
-	('+' / '-' / '*' / '/') _ numeric_expression_operand
+	[-+*/] _ numeric_expression_operand
 
 approximate_numeric_literal <-
 	exact_numeric_literal 'E'
@@ -541,7 +536,7 @@ exact_numeric_literal	<-
 	(unsigned_integer '.')* unsigned_integer
 
 signed_integer <-
-	('+' / '-')? unsigned_integer
+	[-+]? unsigned_integer
 
 # TODO: We should take out character_string_literal here, MD thinks --
 # what sort of use case did people have in mind here?
@@ -566,13 +561,13 @@ unsigned_hexadecimal <-
 	'0x' hex_digit+
 
 digit <-
-	'[0-9]'
+	[0-9]
 
 hex_digit <-
-	'[0-9A-F]'
+	[0-9A-F]
 
 letter <-
-	'[a-zA-Z]'
+	[a-zA-Z]
 
 # Reserved words
 
@@ -684,7 +679,7 @@ ANY_CHAR <-
 	letter / digit / ' ' / '\t' / ',' / '' / '.'
 
 comment	<-
-	'--' '[^\n\r]*'
+	'--' (![\n\r])*
 
 _ <-
 	(comment / Space / EOL)*
@@ -693,10 +688,19 @@ __ <-
 	(comment / Space / EOL)+
 
 _a <-
-	!'[A-Z0-9_]'
+	![A-Z0-9_]
 
 Space <-
 	' '+ / '\t'
 
 EOL <-
 	'\r\n' / '\n' / '\r'
+
+EOF <-
+    !.
+
+# =========================== Configurables for deployers
+# additional prefixes to be added here
+udf_prefix <-
+	'ivo_'
+

From 7524aa9f0f48e6edf02e2d7d980cf769e229ec45 Mon Sep 17 00:00:00 2001
From: "Jon J. C" <juaristi@uni-heidelberg.de>
Date: Wed, 18 Oct 2023 13:20:00 +0200
Subject: [PATCH 2/4] Adapt classical PEG syntax to arpeggio equivalent. Some
 tests fail

---
 src/peg/testpeg.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/src/peg/testpeg.py b/src/peg/testpeg.py
index 685e8fc..1725e10 100644
--- a/src/peg/testpeg.py
+++ b/src/peg/testpeg.py
@@ -48,7 +48,10 @@ def get_parser(debug=False, root='query_specification'):
     peg_rules = re.sub('#', '// ', peg_rules)
 
     # adapt character range syntax
-    peg_rules = re.sub("'\\[", "r'[", peg_rules)
+    peg_rules = re.sub("\\[", "r'[", peg_rules)
+    peg_rules = re.sub("\\!r'\\[", "r'[^", peg_rules)
+    peg_rules = re.sub("\\]", "]'", peg_rules)
+    peg_rules = re.sub("EOF <-[^;]*;", "", peg_rules)
 
     return ParserPEG(peg_rules, 
        root,

From 486116dbf8809f3ee6cd0c2977bf7d63839fa4b7 Mon Sep 17 00:00:00 2001
From: "Jon J. C" <juaristi@uni-heidelberg.de>
Date: Wed, 18 Oct 2023 15:26:57 +0200
Subject: [PATCH 3/4] Remove duplicated rule numeric_primary

---
 src/peg/adql2.1.peg | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/src/peg/adql2.1.peg b/src/peg/adql2.1.peg
index 9172e2c..7203c62 100644
--- a/src/peg/adql2.1.peg
+++ b/src/peg/adql2.1.peg
@@ -477,10 +477,6 @@ user_defined_function <-
 	(_ value_expression (_ ',' _ value_expression)* _)?
 	')'
 
-numeric_primary	<-
-	value_expression_primary
-	/ numeric_value_function
-
 # We need to seriously re-write value_expression because PEG
 # doesn't have an actual longest-match operator.  Thus, we
 # cannot decide on the type of the first operand.

From 216a3d8cd03025056becae73a1d32258a70d9a2d Mon Sep 17 00:00:00 2001
From: "Jon J. C" <juaristi@uni-heidelberg.de>
Date: Wed, 18 Oct 2023 16:59:31 +0200
Subject: [PATCH 4/4] Fix typo

---
 src/peg/adql2.1.peg | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/peg/adql2.1.peg b/src/peg/adql2.1.peg
index 7203c62..d4cf6b7 100644
--- a/src/peg/adql2.1.peg
+++ b/src/peg/adql2.1.peg
@@ -1,6 +1,6 @@
 # Note: in the actual PEG definition comments start with #
 
-# ============================ The Gramma's root symbol
+# ============================ The Grammar's root symbol
 
 query_specification <-
 	with_clause? _