Git issue 477: \v for vertical spacing

Added \p{HorizSpace} (\p{H}) and \p{VertSpace} (\p{V}).

regex_3/_regex_unicode.h

@@ -34,9 +34,9 @@ typedef RE_UINT32 (*RE_GetPropertyFunc)(RE_UINT32 codepoint);
 
 #define RE_PROP_GC 0x1E
 #define RE_PROP_CASED 0xA
-#define RE_PROP_UPPERCASE 0x56
-#define RE_PROP_LOWERCASE 0x33
-#define RE_PROP_SCX 0x50
+#define RE_PROP_UPPERCASE 0x57
+#define RE_PROP_LOWERCASE 0x34
+#define RE_PROP_SCX 0x51
 
 #define RE_PROP_C 30
 #define RE_PROP_L 31
@@ -95,16 +95,16 @@ typedef RE_UINT32 (*RE_GetPropertyFunc)(RE_UINT32 codepoint);
 #define RE_PROP_CNTRL 0x1E0001
 #define RE_PROP_DIGIT 0x1E0009
 #define RE_PROP_GRAPH 0x1F0001
-#define RE_PROP_LOWER 0x330001
-#define RE_PROP_PRINT 0x4B0001
-#define RE_PROP_SPACE 0x580001
-#define RE_PROP_UPPER 0x560001
-#define RE_PROP_WORD 0x590001
-#define RE_PROP_XDIGIT 0x5B0001
-#define RE_PROP_POSIX_ALNUM 0x460001
-#define RE_PROP_POSIX_DIGIT 0x470001
-#define RE_PROP_POSIX_PUNCT 0x480001
-#define RE_PROP_POSIX_XDIGIT 0x490001
+#define RE_PROP_LOWER 0x340001
+#define RE_PROP_PRINT 0x4C0001
+#define RE_PROP_SPACE 0x5A0001
+#define RE_PROP_UPPER 0x570001
+#define RE_PROP_WORD 0x5B0001
+#define RE_PROP_XDIGIT 0x5D0001
+#define RE_PROP_POSIX_ALNUM 0x470001
+#define RE_PROP_POSIX_DIGIT 0x480001
+#define RE_PROP_POSIX_PUNCT 0x490001
+#define RE_PROP_POSIX_XDIGIT 0x4A0001
 
 #define RE_WBREAK_OTHER 0
 #define RE_WBREAK_LF 1
@@ -193,11 +193,11 @@ typedef RE_UINT32 (*RE_GetPropertyFunc)(RE_UINT32 codepoint);
 #define RE_LBREAK_REGIONALINDICATOR 41
 #define RE_LBREAK_EMODIFIER 42
 
-extern char* re_strings[1472];
-extern RE_Property re_properties[173];
+extern char* re_strings[1474];
+extern RE_Property re_properties[177];
 extern RE_PropertyValue re_property_values[1619];
 extern RE_UINT16 re_expand_on_folding[104];
-extern RE_GetPropertyFunc re_get_property[94];
+extern RE_GetPropertyFunc re_get_property[96];
 
 RE_UINT32 re_get_alphabetic(RE_UINT32 codepoint);
 RE_UINT32 re_get_alphanumeric(RE_UINT32 codepoint);
@@ -237,6 +237,7 @@ RE_UINT32 re_get_grapheme_extend(RE_UINT32 codepoint);
 RE_UINT32 re_get_grapheme_link(RE_UINT32 codepoint);
 RE_UINT32 re_get_hangul_syllable_type(RE_UINT32 codepoint);
 RE_UINT32 re_get_hex_digit(RE_UINT32 codepoint);
+RE_UINT32 re_get_horiz_space(RE_UINT32 codepoint);
 RE_UINT32 re_get_hyphen(RE_UINT32 codepoint);
 RE_UINT32 re_get_id_continue(RE_UINT32 codepoint);
 RE_UINT32 re_get_ideographic(RE_UINT32 codepoint);
@@ -287,6 +288,7 @@ RE_UINT32 re_get_terminal_punctuation(RE_UINT32 codepoint);
 RE_UINT32 re_get_unified_ideograph(RE_UINT32 codepoint);
 RE_UINT32 re_get_uppercase(RE_UINT32 codepoint);
 RE_UINT32 re_get_variation_selector(RE_UINT32 codepoint);
+RE_UINT32 re_get_vert_space(RE_UINT32 codepoint);
 RE_UINT32 re_get_white_space(RE_UINT32 codepoint);
 RE_UINT32 re_get_word(RE_UINT32 codepoint);
 RE_UINT32 re_get_word_break(RE_UINT32 codepoint);

regex_3/regex.py

@@ -241,7 +241,7 @@
   "VERSION1", "X", "VERBOSE", "W", "WORD", "error", "Regex", "__version__",
   "__doc__", "RegexFlag"]
 
-__version__ = "2.5.118"
+__version__ = "2.5.119"
 
 # --------------------------------------------------------------------
 # Public interface.

regex_3/test_regex.py

@@ -4321,6 +4321,10 @@ def test_hg_bugs(self):
         self.assertEqual(regex.match(r'(.)+', 'abc').allcaptures(), (['abc'], ['a', 'b', 'c']))
         self.assertEqual(regex.match(r'(.)+', 'abc').allspans(), ([(0, 3)], [(0, 1), (1, 2), (2, 3)]))
 
+        # Git issue 477: \v for vertical spacing
+        self.assertEqual(bool(regex.fullmatch(r'\p{HorizSpace}+', '\t \xA0\u1680\u180E\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200A\u202F\u205F\u3000')), True)
+        self.assertEqual(bool(regex.fullmatch(r'\p{VertSpace}+', '\n\v\f\r\x85\u2028\u2029')), True)
+
     def test_fuzzy_ext(self):
         self.assertEqual(bool(regex.fullmatch(r'(?r)(?:a){e<=1:[a-z]}', 'e')),
           True)

setup.py

@@ -7,7 +7,7 @@
 
 setup(
     name='regex',
-    version='2022.7.25',
+    version='2022.8.17',
     description='Alternative regular expression module, to replace re.',
     long_description=long_description,
     long_description_content_type='text/x-rst',

tools/build_regex_unicode.py

@@ -511,6 +511,9 @@ def make_binary_property(properties, names, codepoints):
     for name in names:
         properties[munge(name)] = property
 
+def make_ranges(*values):
+    return Ranges((value, value) for value in values)
+
 def make_additional_properties(unicode_data):
 
     def get_values(prop_name):
@@ -616,6 +619,16 @@ def get_codepoints(prop_name, val_name):
 
     make_binary_property(properties, ['Posix_XDigit'], posix_xdigit)
 
+    # Make the 'Horiz_Space' property.
+    horiz_space = make_ranges(0x09, 0x20, 0xA0, 0x1680, 0x180E) | Ranges([(0x2000, 0x200A)]) | make_ranges(0x202F, 0x205F, 0x3000)
+
+    make_binary_property(properties, ['Horiz_Space', 'H'], horiz_space)
+
+    # Make the 'Vert_Space' property.
+    vert_space = Ranges([(0x0A, 0x0D)]) | make_ranges(0x85, 0x2028, 0x2029)
+
+    make_binary_property(properties, ['Vert_Space', 'V'], vert_space)
+
 def preferred(d):
     return munge(d['names'][0])
 
@@ -1310,7 +1323,7 @@ def generate_code(unicode_data, tools_folder):
     prop_list = list(unique(properties.values(), key=id))
     prop_list.sort(key=preferred)
 
-    unicode_data['property_tablee_count'] = len(properties)
+    unicode_data['property_table_count'] = len(properties)
     unicode_data['property_count'] = len(prop_list)
 
     no_yes_maybe = {
@@ -1680,7 +1693,7 @@ def make_key(names):
         h_file.write('\n')
 
         h_file.write('extern char* re_strings[{}];\n'.format(unicode_data['string_count']))
-        h_file.write('extern RE_Property re_properties[{}];\n'.format(unicode_data['property_tablee_count']))
+        h_file.write('extern RE_Property re_properties[{}];\n'.format(unicode_data['property_table_count']))
         h_file.write('extern RE_PropertyValue re_property_values[{}];\n'.format(unicode_data['valueset_table_count']))
         h_file.write('extern RE_UINT16 re_expand_on_folding[{}];\n'.format(unicode_data['expanded_count']))
         h_file.write('extern RE_GetPropertyFunc re_get_property[{}];\n'.format(unicode_data['property_count']))