Merge branch 'sb/userdiff-lisp-family'

The userdiff driver for the Scheme language has been extended to
cover other Lisp dialects.

* sb/userdiff-lisp-family:
  userdiff: extend Scheme support to cover other Lisp dialects
  userdiff: tighten word-diff test case of the scheme driver

Documentation/gitattributes.adoc

@@ -911,7 +911,8 @@ patterns are available:
 
 - `rust` suitable for source code in the Rust language.
 
-- `scheme` suitable for source code in the Scheme language.
+- `scheme` suitable for source code in most Lisp dialects,
+  including Scheme, Emacs Lisp, Common Lisp, and Clojure.
 
 - `tex` suitable for source code for LaTeX documents.
 

t/t4018/scheme-lisp-defun-a

@@ -0,0 +1,4 @@
+(defun some-func (x y z) RIGHT
+  (let ((a x)
+        (b y))
+        (ChangeMe a b)))

t/t4018/scheme-lisp-defun-b

@@ -0,0 +1,4 @@
+(macrolet ((foo (x) `(bar ,x)))
+  (defun mumble (x) ; RIGHT
+    (when (> x 0)
+      (foo x)))) ; ChangeMe

t/t4018/scheme-lisp-eval-when

@@ -0,0 +1,4 @@
+(eval-when (:compile-toplevel :load-toplevel :execute)  ; RIGHT
+  (set-macro-character #\?
+		       (lambda (stream char)
+			 `(make-pattern-variable ,(read stream)))))  ; ChangeMe

t/t4018/scheme-module-b

@@ -0,0 +1,6 @@
+(module A
+  (export with-display-exception)
+  (extern (display-exception display-exception))
+  (def (with-display-exception thunk) RIGHT
+    (with-catch (lambda (e) (display-exception e (current-error-port)) e)
+      thunk ChangeMe)))

t/t4034/scheme/expect

@@ -2,10 +2,11 @@
 <BOLD>index 74b6605..63b6ac4 100644<RESET>
 <BOLD>--- a/pre<RESET>
 <BOLD>+++ b/post<RESET>
-<CYAN>@@ -1,6 +1,6 @@<RESET>
+<CYAN>@@ -1,7 +1,7 @@<RESET>
 (define (<RED>myfunc a b<RESET><GREEN>my-func first second<RESET>)
   ; This is a <RED>really<RESET><GREEN>(moderately)<RESET> cool function.
   (<RED>this\place<RESET><GREEN>that\place<RESET> (+ 3 4))
-  (define <RED>some-text<RESET><GREEN>|a greeting|<RESET> "hello")
+  (define <RED>|the \| \greeting|<RESET><GREEN>|a \greeting|<RESET> |hello there|)
+  ({<RED>}<RESET>(([<RED>]<RESET>(func-n)<RED>[<RESET>]))<RED>{<RESET>})
   (let ((c (<RED>+ a b<RESET><GREEN>add1 first<RESET>)))
     (format "one more than the total is %d" (<RED>add1<RESET><GREEN>+<RESET> c <GREEN>second<RESET>))))

t/t4034/scheme/post

@@ -1,6 +1,7 @@
 (define (my-func first second)
   ; This is a (moderately) cool function.
   (that\place (+ 3 4))
-  (define |a greeting| "hello")
+  (define |a \greeting| |hello there|)
+  ({(([(func-n)]))})
   (let ((c (add1 first)))
     (format "one more than the total is %d" (+ c second))))

t/t4034/scheme/pre

@@ -1,6 +1,7 @@
 (define (myfunc a b)
   ; This is a really cool function.
   (this\place (+ 3 4))
-  (define some-text "hello")
+  (define |the \| \greeting| |hello there|)
+  ({}(([](func-n)[])){})
   (let ((c (+ a b)))
     (format "one more than the total is %d" (add1 c))))

userdiff.c

@@ -344,14 +344,24 @@ PATTERNS("rust",
 	 "|[0-9][0-9_a-fA-Fiosuxz]*(\\.([0-9]*[eE][+-]?)?[0-9_fF]*)?"
 	 "|[-+*\\/<>%&^|=!:]=|<<=?|>>=?|&&|\\|\\||->|=>|\\.{2}=|\\.{3}|::"),
 PATTERNS("scheme",
-	 "^[\t ]*(\\(((define|def(struct|syntax|class|method|rules|record|proto|alias)?)[-*/ \t]|(library|module|struct|class)[*+ \t]).*)$",
 	 /*
-	  * R7RS valid identifiers include any sequence enclosed
-	  * within vertical lines having no backslashes
+	  * An unindented opening parenthesis identifies a top-level
+	  * expression in all Lisp dialects.
 	  */
-	 "\\|([^\\\\]*)\\|"
-	 /* All other words should be delimited by spaces or parentheses */
-	 "|([^][)(}{[ \t])+"),
+	 "^(\\(.*)$\n"
+	 /* For Scheme: a possibly indented left paren followed by a keyword. */
+	 "^[\t ]*(\\(((define|def(struct|syntax|class|method|rules|record|proto|alias)?)[-*/ \t]|(library|module|struct|class)[*+ \t]).*)$\n"
+	 /*
+	  * For all Lisp dialects: a slightly indented line starting with "(def".
+	  */
+	 "^  ?(\\([Dd][Ee][Ff].*)$",
+	 /*
+	  * The union of R7RS and Common Lisp symbol syntax: allows arbitrary
+	  * strings between vertical bars, including any escaped characters.
+	  */
+	 "\\|([^|\\\\]|\\\\.)*\\|"
+	 /* All other words should be delimited by spaces or parentheses. */
+	 "|([^][)(}{ \t])+"),
 PATTERNS("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$",
 	 "\\\\[a-zA-Z@]+|\\\\.|([a-zA-Z0-9]|[^\x01-\x7f])+"),
 { .name = "default", .binary = -1 },