Merge branch 'tr/diff-words-test'

* tr/diff-words-test:
t4034 (diff --word-diff): add a minimum Perl drier test vector
t4034 (diff --word-diff): style suggestions
userdiff: simplify word-diff safeguard
t4034: bulk verify builtin word regex sanity

diff --combined userdiff.c
index 9ebf231ea5ee2e7fd1f71c9557a6537d29428d8d,3a1c392bbd76b167847f7a3b164f0135eb66740e..1ff47977d549992ada8c1236187d4516b648ee7d
--- 1/userdiff.c
--- 2/userdiff.c
+++ b/userdiff.c
@@@ -8,9 -8,11 +8,11 @@@ static int ndrivers
  static int drivers_alloc;
  
  #define PATTERNS(name, pattern, word_regex)                   \
-       { name, NULL, -1, { pattern, REG_EXTENDED }, word_regex }
+       { name, NULL, -1, { pattern, REG_EXTENDED },            \
+         word_regex "|[^[:space:]]|[\xc0-\xff][\x80-\xbf]+" }
  #define IPATTERN(name, pattern, word_regex)                   \
-       { name, NULL, -1, { pattern, REG_EXTENDED | REG_ICASE }, word_regex }
+       { name, NULL, -1, { pattern, REG_EXTENDED | REG_ICASE }, \
+         word_regex "|[^[:space:]]|[\xc0-\xff][\x80-\xbf]+" }
  static struct userdiff_driver builtin_drivers[] = {
  IPATTERN("fortran",
         "!^([C*]|[ \t]*!)\n"
@@@ -24,10 -26,9 +26,9 @@@
          * Don't worry about format statements without leading digits since
          * they would have been matched above as a variable anyway. */
         "|[-+]?[0-9.]+([AaIiDdEeFfLlTtXx][Ss]?[-+]?[0-9.]*)?(_[a-zA-Z0-9][a-zA-Z0-9_]*)?"
-        "|//|\\*\\*|::|[/<>=]="
-        "|[^[:space:]]|[\x80-\xff]+"),
+        "|//|\\*\\*|::|[/<>=]="),
  PATTERNS("html", "^[ \t]*(<[Hh][1-6][ \t].*>.*)$",
-        "[^<>= \t]+|[^[:space:]]|[\x80-\xff]+"),
+        "[^<>= \t]+"),
  PATTERNS("java",
         "!^[ \t]*(catch|do|for|if|instanceof|new|return|switch|throw|while)\n"
         "^[ \t]*(([A-Za-z_][A-Za-z_0-9]*[ \t]+)+[A-Za-z_][A-Za-z_0-9]*[ \t]*\\([^;]*)$",
@@@ -35,8 -36,7 +36,7 @@@
         "[a-zA-Z_][a-zA-Z0-9_]*"
         "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
         "|[-+*/<>%&^|=!]="
-        "|--|\\+\\+|<<=?|>>>?=?|&&|\\|\\|"
-        "|[^[:space:]]|[\x80-\xff]+"),
+        "|--|\\+\\+|<<=?|>>>?=?|&&|\\|\\|"),
  PATTERNS("objc",
         /* Negate C statements that can look like functions */
         "!^[ \t]*(do|for|if|else|return|switch|while)\n"
@@@ -49,18 -49,16 +49,16 @@@
         /* -- */
         "[a-zA-Z_][a-zA-Z0-9_]*"
         "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
-        "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"
-        "|[^[:space:]]|[\x80-\xff]+"),
+        "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
  PATTERNS("pascal",
 -       "^((procedure|function|constructor|destructor|interface|"
 +       "^(((class[ \t]+)?(procedure|function)|constructor|destructor|interface|"
                "implementation|initialization|finalization)[ \t]*.*)$"
         "\n"
         "^(.*=[ \t]*(class|record).*)$",
         /* -- */
         "[a-zA-Z_][a-zA-Z0-9_]*"
         "|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
-        "|<>|<=|>=|:=|\\.\\."
-        "|[^[:space:]]|[\x80-\xff]+"),
+        "|<>|<=|>=|:=|\\.\\."),
  PATTERNS("perl",
         "^[ \t]*package .*;\n"
         "^[ \t]*sub .* \\{\n"
@@@ -76,33 -74,29 +74,29 @@@
         "|&&|\\|\\||//|\\+\\+|--|\\*\\*|\\.\\.\\.?"
         "|[-+*/%.^&<>=!|]="
         "|=~|!~"
-        "|<<|<>|<=>|>>"
-        "|[^[:space:]]"),
+        "|<<|<>|<=>|>>"),
  PATTERNS("php",
         "^[\t ]*(((public|protected|private|static)[\t ]+)*function.*)$\n"
         "^[\t ]*(class.*)$",
         /* -- */
         "[a-zA-Z_][a-zA-Z0-9_]*"
         "|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
-        "|[-+*/<>%&^|=!.]=|--|\\+\\+|<<=?|>>=?|===|&&|\\|\\||::|->"
-        "|[^[:space:]]|[\x80-\xff]+"),
+        "|[-+*/<>%&^|=!.]=|--|\\+\\+|<<=?|>>=?|===|&&|\\|\\||::|->"),
  PATTERNS("python", "^[ \t]*((class|def)[ \t].*)$",
         /* -- */
         "[a-zA-Z_][a-zA-Z0-9_]*"
         "|[-+0-9.e]+[jJlL]?|0[xX]?[0-9a-fA-F]+[lL]?"
-        "|[-+*/<>%&^|=!]=|//=?|<<=?|>>=?|\\*\\*=?"
-        "|[^[:space:]]|[\x80-\xff]+"),
+        "|[-+*/<>%&^|=!]=|//=?|<<=?|>>=?|\\*\\*=?"),
         /* -- */
  PATTERNS("ruby", "^[ \t]*((class|module|def)[ \t].*)$",
         /* -- */
         "(@|@@|\\$)?[a-zA-Z_][a-zA-Z0-9_]*"
         "|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+|\\?(\\\\C-)?(\\\\M-)?."
-        "|//=?|[-+*/<>%&^|=!]=|<<=?|>>=?|===|\\.{1,3}|::|[!=]~"
-        "|[^[:space:]]|[\x80-\xff]+"),
+        "|//=?|[-+*/<>%&^|=!]=|<<=?|>>=?|===|\\.{1,3}|::|[!=]~"),
  PATTERNS("bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$",
         "[={}\"]|[^={}\" \t]+"),
  PATTERNS("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$",
-        "\\\\[a-zA-Z@]+|\\\\.|[a-zA-Z0-9\x80-\xff]+|[^[:space:]]"),
+        "\\\\[a-zA-Z@]+|\\\\.|[a-zA-Z0-9\x80-\xff]+"),
  PATTERNS("cpp",
         /* Jump targets or access declarations */
         "!^[ \t]*[A-Za-z_][A-Za-z_0-9]*:.*$\n"
@@@ -113,8 -107,7 +107,7 @@@
         /* -- */
         "[a-zA-Z_][a-zA-Z0-9_]*"
         "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
-        "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"
-        "|[^[:space:]]|[\x80-\xff]+"),
+        "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
  PATTERNS("csharp",
         /* Keywords */
         "!^[ \t]*(do|while|for|if|else|instanceof|new|return|switch|case|throw|catch|using)\n"
@@@ -129,8 -122,7 +122,7 @@@
         /* -- */
         "[a-zA-Z_][a-zA-Z0-9_]*"
         "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
-        "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"
-        "|[^[:space:]]|[\x80-\xff]+"),
+        "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
  { "default", NULL, -1, { NULL, 0 } },
  };
  #undef PATTERNS