moar grammars for the Zoo

git-svn-id: https://slps.svn.sourceforge.net/svnroot/slps@802 ab42f6e0-554d-0410-b580-99e487e6eeb2

COPYRIGHT.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2008, Contributors to the SLPS project
+Copyright (c) 2008–2010, Contributors to the SLPS project
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

shared/tools/pdf2bgf

@@ -22,7 +22,8 @@ elif [ ! -r $4 ]; then
     echo "Oops: $1 not found or not readable."
     exit 1
 else
-	python ${SLPS}/topics/extraction/bnf2bgf/pdf2lll.py $1 intermediate.lll $3 $4
+    python ${SLPS}/topics/extraction/bnf2bgf/pdf2lll.py $1 intermediate.lll $3 $4
     python ${SLPS}/topics/extraction/bnf2bgf/lll2bgf.py intermediate.lll $2
-	#rm -f intermediate.lll
+    #rm -f intermediate.lll
 fi
+

topics/extraction/bnf2bgf/lll2bgf.py

@@ -125,6 +125,7 @@ def serialiseExpression(ts,debug):
 def serialiseFormula(name,tokens):
 	# Useful yet annoying
 	#print 'Processing',name,'...'
+	# Replace BREAKPOINT with the name of a nonterminal you like to debug
 	if name=='BREAKPOINT':
 		print tokens
 		return '<bgf:production><nonterminal>'+name+'</nonterminal>'+serialiseExpression(tokens,True)+'</bgf:production>'

topics/extraction/bnf2bgf/pdf2lll.py

@@ -160,7 +160,7 @@ def readLines(f):
 				lines.append(line)
 	pdf.close()
 
-def readGrammar(f):
+def readGrammar(lines):
 	print 'Reading the PDF contents...'
 	for line in lines:
 		#print line

topics/grammars/cpp/Makefile

@@ -1,8 +1,11 @@
 build:
 	cd iso-14882-1998 && make build
+	cd iso-n2723 && make build
 
 clean:
 	cd iso-14882-1998 && make clean
+	cd iso-n2723 && make clean
 
 test:
 	cd iso-14882-1998 && make test
+	cd iso-n2723 && make test

topics/grammars/cpp/iso-n2723/Makefile

@@ -0,0 +1,15 @@
+build:
+	grep -xv 'c ' iso-is-annex.txt > iso-is-annex-no-c.txt
+	perl -pi -w -e 's/hand ler/handler/g;' iso-is-annex-no-c.txt
+	../../../../shared/tools/pdf2bgf iso-is-annex-no-c.txt iso-output.bgf banned-lines.lst keywords.lst
+	../../../../shared/tools/checkxml bgf iso-output.bgf
+	../../../../shared/tools/normbgf iso-output.bgf iso-is-grammar.bgf
+	../../../../shared/tools/bgf2bnf iso-is-grammar.bgf iso-is.bnf
+	rm -f iso-output.bgf
+
+clean:
+	rm -f iso-output.bgf iso-is-grammar.bgf iso-is.bnf iso-is-annex-no-c.txt intermediate.lll
+
+test:
+	make build
+	../../../../shared/tools/gdt iso-is-grammar.bgf extracted-grammar.bgf

topics/grammars/cpp/iso-n2723/README.txt

@@ -0,0 +1,21 @@
+Doc No: N2723=08-0233 
+Date: 2008-08-25 
+Reply to: Pete Becker 
+Roundhouse Consulting, Ltd. 
+pete@versatilecoding.com 
+Working Draft, Standard for Programming 
+Language C++
+
+Note: this is an early draft. It’s known to be incomplet and incorrekt, and it has lots of ba d 
+format ting.
+
+© ISO/IEC
+
+Fixes that were necessary for extraction:
+
+	'handler' is for some reason typeset as 'hand ler'
+		fixed by a perl regexp inline replace
+
+	'(c)' was copy-pasted as two lines
+		'c ' lines are removed by a negative grep
+

topics/grammars/cpp/iso-n2723/banned-lines.lst

@@ -0,0 +1,3 @@
+ISO/IEC N2723
+§ A.
+gram.