1.5a3 prerelease 1 from AMK

Lib/re.py

@@ -317,10 +317,19 @@ class Eol(Instruction):
 
 class Set(Instruction):
     name = 'set'
-    def __init__(self, set):
+    def __init__(self, set, flags=0):
 	self.set = set
-	Instruction.__init__(self, chr(3), 33)
+	if flags & IGNORECASE: self.set=map(string.lower, self.set)
+	if len(set)==1: 
+	    # If only one element, use the "exact" opcode (it'll be faster)
+	    Instruction.__init__(self, chr(4), 2)
+	else:
+	    # Use the "set" opcode
+	    Instruction.__init__(self, chr(3), 33)
     def assemble(self, position, labels):
+	if len(self.set)==1:
+	    # If only one character in set, generate an "exact" opcode
+	    return self.opcode + self.set[0]
 	result = self.opcode
 	temp = 0
 	for i, c in map(lambda x: (x, chr(x)), range(256)):
@@ -333,14 +342,16 @@ class Set(Instruction):
     def __repr__(self):
 	result = '%-15s' % (self.name)
 	self.set.sort()
+	# XXX this should print more intelligently
 	for char in self.set:
 	    result = result + char
 	return result
     
 class Exact(Instruction):
     name = 'exact'
-    def __init__(self, char):
+    def __init__(self, char, flags):
 	self.char = char
+	if flags & IGNORECASE: self.char=string.lower(self.char)
 	Instruction.__init__(self, chr(4), 2)
     def assemble(self, position, labels):
 	return self.opcode + self.char
@@ -881,7 +892,7 @@ def compile(pattern, flags=0):
 	    escape_type, value, index = expand_escape(pattern, index)
 
 	    if escape_type == CHAR:
-		stack.append([Exact(value)])
+		stack.append([Exact(value, flags)])
 		lastop = '\\' + value
 		
 	    elif escape_type == MEMORY_REFERENCE:
@@ -1306,7 +1317,7 @@ def compile(pattern, flags=0):
 
 	elif char == '.':
 	    if flags & DOTALL:
-		stack.append([Set(map(chr, range(256)))])
+		stack.append([Set(map(chr, range(256)), flags)])
 	    else:
 		stack.append([AnyChar()])
 	    lastop = '.'
@@ -1336,12 +1347,12 @@ def compile(pattern, flags=0):
 		    index = end + 1
 		# do not change lastop
 	    else:
-		stack.append([Exact(char)])
+		stack.append([Exact(char, flags)])
 		lastop = '#'
 
 	elif char in string.whitespace:
 	    if not (flags & VERBOSE):
-		stack.append([Exact(char)])
+		stack.append([Exact(char, flags)])
 		lastop = char
 
 	elif char == '[':
@@ -1449,22 +1460,25 @@ def compile(pattern, flags=0):
 	    index = index + 1
 
 	    if negate:
+		# If case is being ignored, then both upper- and lowercase
+		# versions of the letters must be excluded.
+		if flags & IGNORECASE: set=set+map(string.upper, set)
 		notset = []
 		for char in map(chr, range(256)):
 		    if char not in set:
 			notset.append(char)
 		if len(notset) == 0:
 		    raise error, 'empty negated set'
-		stack.append([Set(notset)])
+		stack.append([Set(notset, flags)])
 	    else:
 		if len(set) == 0:
 		    raise error, 'empty set'
-		stack.append([Set(set)])
+		stack.append([Set(set, flags)])
 
 	    lastop = '[]'
 
 	else:
-	    stack.append([Exact(char)])
+	    stack.append([Exact(char, flags)])
 	    lastop = char
 
     code = []
@@ -1485,6 +1499,7 @@ def compile(pattern, flags=0):
 	code.append(Label(label))
 	label = label + 1
     code.append(End())
+#    print code
     return RegexObject(pattern, flags, code, register, groupindex)
 
 # Replace expand_escape and _expand functions with their C equivalents.

Lib/test/re_tests.py

@@ -318,6 +318,7 @@ tests = [
 #    ('((((((((((a))))))))))\\41', 'aa', FAIL),
 #    ('((((((((((a))))))))))\\41', 'a!', SUCCEED, 'found', 'a!'),
     ('((((((((((a))))))))))\\41', '', SYNTAX_ERROR),
+    ('(?i)((((((((((a))))))))))\\41', '', SYNTAX_ERROR),
     ('(((((((((a)))))))))', 'a', SUCCEED, 'found', 'a'),
     ('multiple words of text', 'uh-uh', FAIL),
     ('multiple words', 'multiple words, yeah', SUCCEED, 'found', 'multiple words'),
@@ -448,7 +449,6 @@ tests = [
     ('(?i)((((((((((a))))))))))\\10', 'AA', SUCCEED, 'found', 'AA'),
     #('(?i)((((((((((a))))))))))\\41', 'AA', FAIL),
     #('(?i)((((((((((a))))))))))\\41', 'A!', SUCCEED, 'found', 'A!'),
-    ('(?i)((((((((((a))))))))))\\41', '', SYNTAX_ERROR),
     ('(?i)(((((((((a)))))))))', 'A', SUCCEED, 'found', 'A'),
     ('(?i)(?:(?:(?:(?:(?:(?:(?:(?:(?:(a))))))))))', 'A', SUCCEED, 'g1', 'A'),
     ('(?i)(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))', 'C', SUCCEED, 'g1', 'C'),
@@ -506,10 +506,21 @@ xyzabc
     ('a.b', 'a\nb', FAIL),
     ('(?s)a.b', 'a\nb', SUCCEED, 'found', 'a\nb'),
 
-    # test \w, etc.
+    # test \w, etc. both inside and outside character classes
 
     ('\\w+', '--ab_cd0123--', SUCCEED, 'found', 'ab_cd0123'),
+    ('[\\w]+', '--ab_cd0123--', SUCCEED, 'found', 'ab_cd0123'),
     ('\\D+', '1234abc5678', SUCCEED, 'found', 'abc'),
+    ('[\\D]+', '1234abc5678', SUCCEED, 'found', 'abc'),
     ('[\\da-fA-F]+', '123abc', SUCCEED, 'found', '123abc'),
     ('[\\d-x]', '-', SYNTAX_ERROR),
+    (r'([\s]*)([\S]*)([\s]*)', ' testing!1972', SUCCEED, 'g3+g2+g1', 'testing!1972 '),
+    (r'(\s*)(\S*)(\s*)', ' testing!1972', SUCCEED, 'g3+g2+g1', 'testing!1972 '),
+
+    (r'\xff', '\377', SUCCEED, 'found', chr(255)),
+    (r'\x00ff', '\377', SUCCEED, 'found', chr(255)),
+    (r'\t\n\v\r\f\a\g', '\t\n\v\r\f\ag', SUCCEED, 'found', '\t\n\v\r\f\ag'),
+    ('\t\n\v\r\f\a\g', '\t\n\v\r\f\ag', SUCCEED, 'found', '\t\n\v\r\f\ag'),
+    (r'\t\n\v\r\f\a', '\t\n\v\r\f\a', SUCCEED, 'found', chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7)),
+    (r'[\t][\n][\v][\r][\f][\a][\A][\b][\B][\Z][\g]', '\t\n\v\r\f\aA\bBZg', SUCCEED, 'found', '\t\n\v\r\f\aA\bBZg'),
 ]

Lib/test/regex_tests.py

@@ -278,6 +278,12 @@ tests = [
 ('\\([xyz]*\\)x', 'abcx', SUCCEED,
  'found+"-"+g1', 'x-'),
 ('\\(a\\)+b\\|aac', 'aac', SUCCEED,
- 'found+"-"+g1', 'aac-None')
+ 'found+"-"+g1', 'aac-None'),
+('\<a', 'a', SUCCEED, 'found', 'a'),
+('\<a', '!', FAIL),
+('a\<b', 'ab', FAIL),
+('a\>', 'ab', FAIL),
+('a\>', 'a!', SUCCEED, 'found', 'a'),
+('a\>', 'a', SUCCEED, 'found', 'a'),
 ]
 

Lib/test/test_re.py

@@ -31,6 +31,10 @@ try:
 
     assert re.sub('(?P<a>x)', '\g<a>\g<a>', 'xx') == 'xxxx'
 
+    assert re.sub('a', r'\t\n\v\r\f\a\b\B\Z\a\A\w\W\s\S\d\D', 'a') == '\t\n\v\r\f\a\bBZ\aAwWsSdD'
+    assert re.sub('a', '\t\n\v\r\f\a', 'a') == '\t\n\v\r\f\a'
+    assert re.sub('a', '\t\n\v\r\f\a', 'a') == (chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7))
+
 except AssertionError:
     raise TestFailed, "re.sub"
 
@@ -120,7 +124,6 @@ if verbose:
     print 'Running re_tests test suite'
 
 for t in tests:
-    print t
     sys.stdout.flush()
     pattern=s=outcome=repl=expected=None
     if len(t)==5:
@@ -136,6 +139,7 @@ for t in tests:
 	if outcome==SYNTAX_ERROR: pass	# Expected a syntax error
 	else: 
 	    print '=== Syntax error:', t
+    except KeyboardInterrupt: raise KeyboardInterrupt
     except:
 	print '*** Unexpected error ***'
 	if verbose:
@@ -182,3 +186,10 @@ for t in tests:
 		    print repr(repl)+' should be '+repr(expected)
 	    else:
 		print '=== Failed incorrectly', t
+
+            # Try the match with IGNORECASE enabled, and check that it
+	    # still succeeds.
+            obj=re.compile(pattern, re.IGNORECASE)
+            result=obj.search(s)
+            if result==None:
+                print '=== Fails on case-insensitive match', t

Modules/regexmodule.c

@@ -132,8 +132,10 @@ regobj_match(re, args)
 	re->re_lastok = NULL;
 	result = re_match(&re->re_patbuf, buffer, size, offset, &re->re_regs);
 	if (result < -1) {
-		/* Failure like stack overflow */
-		PyErr_SetString(RegexError, "match failure");
+		/* Serious failure of some sort; if re_match didn't 
+		   set an exception, raise a generic error */
+	        if (!PyErr_Occurred())
+		        PyErr_SetString(RegexError, "match failure");
 		return NULL;
 	}
 	if (result >= 0) {
@@ -174,8 +176,10 @@ regobj_search(re, args)
 	result = re_search(&re->re_patbuf, buffer, size, offset, range,
 			   &re->re_regs);
 	if (result < -1) {
-		/* Failure like stack overflow */
-		PyErr_SetString(RegexError, "match failure");
+		/* Serious failure of some sort; if re_match didn't 
+		   set an exception, raise a generic error */
+	        if (!PyErr_Occurred())
+	  	        PyErr_SetString(RegexError, "match failure");
 		return NULL;
 	}
 	if (result >= 0) {

Modules/regexpr.h

@@ -33,16 +33,16 @@ extern "C" {
 
 typedef struct re_pattern_buffer
 {
-	char *buffer;          /* compiled pattern */
+	unsigned char *buffer;          /* compiled pattern */
 	int allocated;         /* allocated size of compiled pattern */
 	int used;              /* actual length of compiled pattern */
-	char *fastmap;         /* fastmap[ch] is true if ch can start pattern */
-	char *translate;       /* translation to apply during compilation/matching */
-	char fastmap_accurate; /* true if fastmap is valid */
-	char can_be_null;      /* true if can match empty string */
-	char uses_registers;   /* registers are used and need to be initialized */
+	unsigned char *fastmap;         /* fastmap[ch] is true if ch can start pattern */
+	unsigned char *translate;       /* translation to apply during compilation/matching */
+	unsigned char fastmap_accurate; /* true if fastmap is valid */
+	unsigned char can_be_null;      /* true if can match empty string */
+	unsigned char uses_registers;   /* registers are used and need to be initialized */
 	int num_registers;     /* number of registers used */
-	char anchor;           /* anchor: 0=none 1=begline 2=begbuf */
+	unsigned char anchor;           /* anchor: 0=none 1=begline 2=begbuf */
 } *regexp_t;
 
 typedef struct re_registers
@@ -93,7 +93,7 @@ extern int re_syntax;
 /* This is the actual syntax mask.  It was added so that Python could do
  * syntax-dependent munging of patterns before compilation. */
 
-extern char re_syntax_table[256];
+extern unsigned char re_syntax_table[256];
 
 void re_compile_initialize(void);
 
@@ -101,7 +101,7 @@ int re_set_syntax(int syntax);
 /* This sets the syntax to use and returns the previous syntax.  The
  * syntax is specified by a bit mask of the above defined bits. */
 
-char *re_compile_pattern(char *regex, int regex_size, regexp_t compiled);
+unsigned char *re_compile_pattern(unsigned char *regex, int regex_size, regexp_t compiled);
 /* This compiles the regexp (given in regex and length in regex_size).
  * This returns NULL if the regexp compiled successfully, and an error
  * message if an error was encountered.  The buffer field must be
@@ -110,14 +110,14 @@ char *re_compile_pattern(char *regex, int regex_size, regexp_t compiled);
  * buffer is NULL).  Also, the translate field must be set to point to a
  * valid translation table, or NULL if it is not used. */
 
-int re_match(regexp_t compiled, char *string, int size, int pos,
+int re_match(regexp_t compiled, unsigned char *string, int size, int pos,
 	     regexp_registers_t old_regs);
 /* This tries to match the regexp against the string.  This returns the
  * length of the matched portion, or -1 if the pattern could not be
  * matched and -2 if an error (such as failure stack overflow) is
  * encountered. */
 
-int re_search(regexp_t compiled, char *string, int size, int startpos,
+int re_search(regexp_t compiled, unsigned char *string, int size, int startpos,
 	      int range, regexp_registers_t regs);
 /* This rearches for a substring matching the regexp.  This returns the
  * first index at which a match is found.  range specifies at how many
@@ -132,28 +132,16 @@ void re_compile_fastmap(regexp_t compiled);
  * the calling program must have initialized the fastmap field to point
  * to an array of 256 characters. */
 
-char *re_comp(char *s);
-/* BSD 4.2 regex library routine re_comp.  This compiles the regexp into
- * an internal buffer.  This returns NULL if the regexp was compiled
- * successfully, and an error message if there was an error. */
-
-int re_exec(char *s);
-/* BSD 4.2 regexp library routine re_exec.  This returns true if the
- * string matches the regular expression (that is, a matching part is
- * found anywhere in the string). */
-
 #else /* HAVE_PROTOTYPES */
 
 extern int re_syntax;
-extern char re_syntax_table[256];
+extern unsigned char re_syntax_table[256];
 void re_compile_initialize();
 int re_set_syntax();
-char *re_compile_pattern();
+unsigned char *re_compile_pattern();
 int re_match();
 int re_search();
 void re_compile_fastmap();
-char *re_comp();
-int re_exec();
 
 #endif /* HAVE_PROTOTYPES */
 

Modules/reopmodule.c

@@ -62,7 +62,7 @@ static PyObject *ReopError;	/* Exception */
 #define BEGINNING_OF_BUFFER	7
 #define END_OF_BUFFER		8
 
-static char *reop_casefold;
+static unsigned char *reop_casefold;
 
 static PyObject *
 makeresult(regs, num_regs)
@@ -105,7 +105,7 @@ reop_match(self, args)
 	PyObject *self;
 	PyObject *args;
 {
-	char *string;
+	unsigned char *string;
 	int fastmaplen, stringlen;
 	int can_be_null, anchor, i;
 	int flags, pos, result;
@@ -163,8 +163,8 @@ reop_match(self, args)
 
 	if (result < -1) {
 		/* Failure like stack overflow */
-		PyErr_SetString(ReopError, "match failure");
-		
+	        if (!PyErr_Occurred())
+	  	        PyErr_SetString(ReopError, "match failure");
 		return NULL;
 	}
 	if (result == -1) {
@@ -174,12 +174,38 @@ reop_match(self, args)
 	return makeresult(&re_regs, bufp.num_registers);
 }
 
+#if 0
+static PyObject *
+reop_optimize(self, args)
+	PyObject *self;
+	PyObject *args;
+{
+  unsigned char *buffer;
+  int buflen;
+  struct re_pattern_buffer bufp;
+
+  PyObject *opt_code;
+  
+  if (!PyArg_Parse(args, "(s#)", &buffer, &buflen)) return NULL;
+  /* Create a new string for the optimized code */
+  opt_code=PyString_FromStringAndSize(buffer, buflen);
+  if (opt_code!=NULL)
+    {
+      bufp.buffer = PyString_AsString(opt_code);
+      bufp.used=bufp.allocated=buflen;
+      
+    }
+  return opt_code;
+  
+}
+#endif
+
 static PyObject *
 reop_search(self, args)
 	PyObject *self;
 	PyObject *args;
 {
-	char *string;
+	unsigned char *string;
 	int fastmaplen, stringlen;
 	int can_be_null, anchor, i;
 	int flags, pos, result;
@@ -237,7 +263,8 @@ reop_search(self, args)
 
 	if (result < -1) {
 		/* Failure like stack overflow */
-		PyErr_SetString(ReopError, "match failure");
+	        if (!PyErr_Occurred())
+	  	        PyErr_SetString(ReopError, "match failure");
 		return NULL;
 	}
 
@@ -626,7 +653,7 @@ reop__expand(self, args)
 {
   PyObject *results, *match_obj;
   PyObject *repl_obj, *newstring;
-  char *repl;
+  unsigned char *repl;
   int size, total_len, i, start, pos;
 
   if (!PyArg_ParseTuple(args, "OS", &match_obj, &repl_obj)) 
@@ -810,7 +837,7 @@ internal_split(args, retain)
   reopobject *pattern;
   int maxsplit=0, count=0, length, next=0, result;
   int match_end=0; /* match_start is defined below */
-  char *start;
+  unsigned char *start;
 
   if (!PyArg_ParseTuple(args, "s#Oi", &start, &length, &pattern,
 			&maxsplit))
@@ -911,6 +938,7 @@ static struct PyMethodDef reop_global_methods[] = {
 	{"expand_escape", reop_expand_escape, 1},
 	{"_expand", reop__expand, 1},
 #if 0
+	{"_optimize",	reop_optimize, 0},
 	{"split",  reop_split, 0},
 	{"splitx",  reop_splitx, 0},
 #endif
@@ -922,8 +950,8 @@ initreop()
 {
 	PyObject *m, *d, *k, *v, *o;
 	int i;
-	char *s;
-	char j[2];
+	unsigned char *s;
+	unsigned char j[2];
 
 	re_compile_initialize();
 
@@ -936,7 +964,7 @@ initreop()
 		goto finally;
 	
 	/* Initialize reop.casefold constant */
-	if (!(v = PyString_FromStringAndSize((char *)NULL, 256)))
+	if (!(v = PyString_FromStringAndSize((unsigned char *)NULL, 256)))
 		goto finally;
 	
 	if (!(s = PyString_AsString(v)))