Added doubled word warnings.

rhettinger · rhettinger · commit e41d4c8ec9b8 · 2003-08-25T04:39:55.000Z
diff --git a/Doc/ref/ref3.tex b/Doc/ref/ref3.tex
@@ -1740,7 +1740,7 @@ \subsection{Additional methods for emulation of sequence types
 indexes by the built-in sequence types, and the \method{__*item__()}
 methods are expected to do this as well.  However, since they should
 already be doing that, negative indexes cannot be passed in; they must
-be be constrained to the bounds of the sequence before being passed to
+be constrained to the bounds of the sequence before being passed to
 the \method{__*item__()} methods.
 Calling \code{max(0, i)} conveniently returns the proper value.
 
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -55,6 +55,8 @@ Library
 Tools/Demos
 -----------
 
+- texcheck.py now detects double word errors.
+
 - md5sum.py mistakenly opened input files in text mode by default, a
   silent and dangerous change from previous releases.  It once again
   opens input files in binary mode by default.  The -t and -b flags
diff --git a/Tools/scripts/texcheck.py b/Tools/scripts/texcheck.py
@@ -98,6 +98,7 @@ def checkit(source, opts, morecmds=[]):
 
     delimiters = re.compile(r'\\(begin|end){([_a-zA-Z]+)}|([()\[\]])')
     braces = re.compile(r'({)|(})')
+    doubledwords = re.compile(r'(\b[A-za-z]+\b) \b\1\b')
 
     openers = []                            # Stack of pending open delimiters
     bracestack = []                         # Stack of pending open braces
@@ -175,6 +176,8 @@ def checkit(source, opts, morecmds=[]):
         if 'e.g.' in line or 'i.e.' in line:
             print r'Style warning, avoid use of i.e or e.g. on line %d' % (lineno,)
 
+        for dw in doubledwords.findall(line):
+            print r'Doubled word warning.  "%s" on line %d' % (dw, lineno)
 
     lastline = lineno
     for lineno, symbol in openers:
