Use Perl non-greedy regex in tokenizer

We can now exclude C++ style comments and #includes,
in addition to C-style comments and strings.

lib.py

@@ -39,15 +39,8 @@ def scriptLines (*args):
 
 def unescape (bstr):
     subs = (
-        ('<','\033[32m/*'),
-        ('>','*/\033[0m'),
-        ('{','\033[33m"'),
-        ('}','"\033[0m'),
         ('\1','\n'),
-        ('\3','<'),
-        ('\4','>'),
-        ('\5','{'),
-        ('\6','}'))
+    )
     for a,b in subs:
         a = a.encode()
         b = b.encode()

script.sh

@@ -148,14 +148,8 @@ case $cmd in
         fi
 
         git cat-file blob $ref 2>/dev/null |
-        tr '\n%<>{}' '\1\2\3\4\5\6' |
-        sed 's/\/\*/</g' |
-        sed 's/\*\//>/g' |
-        sed 's/\\"/%/g' |
-        sed 's/"\([^"]*\)"/{\1}/g' |
-        sed 's/%/\\"/g' |
-        tr '\2' '%' |
-        sed -r 's/(\W*)(<[^>]*>)?(\{[^}]*\})?(\w*)/\1\2\3\n\4\n/g' |
+        tr '\n' '\1' |
+        perl -pe 's%((/\*.*?\*/|//.*?\001|".*?"|#include *<.*?>|\W)+)(\w+)?%\1\n\3\n%g' |
         head -n -1
         ;;