New file: awkreg-grammar.txt.

2 files changed, 74 insertions, 0 deletions

diff --git a/ChangeLog b/ChangeLog
index 7f4faff..1261b64 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,10 @@
 2014-03-17  Kaz Kylheku  <kaz@kylheku.com>
 
+	* awkreg-grammar.txt: New file. Taken from my original Usenet
+	posting in comp.lang.awk.
+
+2014-03-17  Kaz Kylheku  <kaz@kylheku.com>
+
 	Fix in {m,n} syntax.
 
 	The issue is that the parser partially consumes broken {m,n}
diff --git a/awkreg-grammar.txt b/awkreg-grammar.txt
new file mode 100644
index 0000000..af6984b
--- /dev/null
+++ b/awkreg-grammar.txt
@@ -0,0 +1,69 @@
+#######################
+# Original LR grammar #
+#######################
+
+S -> <^> R <$>
+
+R -> R|R
+  -> R+
+  -> R?
+  -> R*
+  -> R R
+  -> R{num<,<num>>}
+  -> R{<,num>}
+  -> (R)
+  -> bracket
+  -> rchar
+
+bracket -> [<^> <bchar / range / class >*]
+
+bchar -> any character but [ or -
+    -> \]
+    -> \-
+    -> \^
+    -> \\
+
+range -> bchar - bchar
+
+class -> [:alpha:] / [:digit:] / ... et cetera
+
+rchar -> any character but ( ) [ ] { } * ? +
+      -> \ char
+
+char  -> any character
+
+#################
+# Left-factored #
+#################
+
+R -> T                  # regex is a single term
+  -> T R                # a term followed by a regex
+  -> T | R              # a term or regex
+  ->                    # empty
+
+T -> F                  # a regex term is a factor
+  -> F *
+  -> F ?
+  -> F +
+  -> F {num<,<num>>}
+
+F -> rchar             # a factor is a regex char
+  -> bracket            # [...] expression
+  -> (R)                # parenthesized regex
+
+bracket -> [<^> <bchar / range / class >*]
+
+bchar -> any character but [ or -
+      -> \]
+      -> \-
+      -> \^
+      -> \\
+
+range -> bchar - bchar
+
+class -> [:alpha:] / [:digit:] / ... et cetera
+
+rchar -> any character but ( ) [ ] { } * ? +
+      -> \ char
+
+char  -> any character