Explain the \p{} and \P{} error message better and

have prettier prettyprint in In.pl.

p4raw-id: //depot/perl@9899

diff --git a/lib/unicode/In.pl b/lib/unicode/In.pl
index eefec27..e0b7a5a 100644 (file)
--- a/lib/unicode/In.pl
+++ b/lib/unicode/In.pl
@@ -2,100 +2,100 @@
 # This file is built by mktables.PL from e.g. Unicode.txt.
 # Any changes made here will be lost!
 %utf8::In = (
-'BasicLatin' => 0,
-'Latin1Supplement' => 1,
-'Hebrew' => 10,
-'Arabic' => 11,
-'Syriac' => 12,
-'Thaana' => 13,
-'Devanagari' => 14,
-'Bengali' => 15,
-'Gurmukhi' => 16,
-'Gujarati' => 17,
-'Oriya' => 18,
-'Tamil' => 19,
-'LatinExtendedA' => 2,
-'Telugu' => 20,
-'Kannada' => 21,
-'Malayalam' => 22,
-'Sinhala' => 23,
-'Thai' => 24,
-'Lao' => 25,
-'Tibetan' => 26,
-'Myanmar' => 27,
-'Georgian' => 28,
-'HangulJamo' => 29,
-'LatinExtendedB' => 3,
-'Ethiopic' => 30,
-'Cherokee' => 31,
-'UnifiedCanadianAboriginalSyllabics' => 32,
-'Ogham' => 33,
-'Runic' => 34,
-'Khmer' => 35,
-'Mongolian' => 36,
-'LatinExtendedAdditional' => 37,
-'GreekExtended' => 38,
-'GeneralPunctuation' => 39,
-'IPAExtensions' => 4,
-'SuperscriptsandSubscripts' => 40,
-'CurrencySymbols' => 41,
-'CombiningMarksforSymbols' => 42,
-'LetterlikeSymbols' => 43,
-'NumberForms' => 44,
-'Arrows' => 45,
-'MathematicalOperators' => 46,
-'MiscellaneousTechnical' => 47,
-'ControlPictures' => 48,
-'OpticalCharacterRecognition' => 49,
-'SpacingModifierLetters' => 5,
-'EnclosedAlphanumerics' => 50,
-'BoxDrawing' => 51,
-'BlockElements' => 52,
-'GeometricShapes' => 53,
-'MiscellaneousSymbols' => 54,
-'Dingbats' => 55,
-'BraillePatterns' => 56,
-'CJKRadicalsSupplement' => 57,
-'KangxiRadicals' => 58,
-'IdeographicDescriptionCharacters' => 59,
-'CombiningDiacriticalMarks' => 6,
-'CJKSymbolsandPunctuation' => 60,
-'Hiragana' => 61,
-'Katakana' => 62,
-'Bopomofo' => 63,
-'HangulCompatibilityJamo' => 64,
-'Kanbun' => 65,
-'BopomofoExtended' => 66,
-'EnclosedCJKLettersandMonths' => 67,
-'CJKCompatibility' => 68,
-'CJKUnifiedIdeographsExtensionA' => 69,
-'Greek' => 7,
-'CJKUnifiedIdeographs' => 70,
-'YiSyllables' => 71,
-'YiRadicals' => 72,
-'HangulSyllables' => 73,
-'HighSurrogates' => 74,
-'HighPrivateUseSurrogates' => 75,
-'LowSurrogates' => 76,
-'PrivateUse' => 77,
-'CJKCompatibilityIdeographs' => 78,
-'AlphabeticPresentationForms' => 79,
-'Cyrillic' => 8,
-'ArabicPresentationFormsA' => 80,
-'CombiningHalfMarks' => 81,
-'CJKCompatibilityForms' => 82,
-'SmallFormVariants' => 83,
-'ArabicPresentationFormsB' => 84,
-'Specials' => 85,
-'HalfwidthandFullwidthForms' => 86,
-'OldItalic' => 87,
-'Gothic' => 88,
-'Deseret' => 89,
-'Armenian' => 9,
-'ByzantineMusicalSymbols' => 90,
-'MusicalSymbols' => 91,
-'MathematicalAlphanumericSymbols' => 92,
-'CJKUnifiedIdeographsExtensionB' => 93,
-'CJKCompatibilityIdeographsSupplement' => 94,
-'Tags' => 95,
+'BasicLatin'                            =>   0,
+'Latin1Supplement'                      =>   1,
+'LatinExtendedA'                        =>   2,
+'LatinExtendedB'                        =>   3,
+'IPAExtensions'                         =>   4,
+'SpacingModifierLetters'                =>   5,
+'CombiningDiacriticalMarks'             =>   6,
+'Greek'                                 =>   7,
+'Cyrillic'                              =>   8,
+'Armenian'                              =>   9,
+'Hebrew'                                =>  10,
+'Arabic'                                =>  11,
+'Syriac'                                =>  12,
+'Thaana'                                =>  13,
+'Devanagari'                            =>  14,
+'Bengali'                               =>  15,
+'Gurmukhi'                              =>  16,
+'Gujarati'                              =>  17,
+'Oriya'                                 =>  18,
+'Tamil'                                 =>  19,
+'Telugu'                                =>  20,
+'Kannada'                               =>  21,
+'Malayalam'                             =>  22,
+'Sinhala'                               =>  23,
+'Thai'                                  =>  24,
+'Lao'                                   =>  25,
+'Tibetan'                               =>  26,
+'Myanmar'                               =>  27,
+'Georgian'                              =>  28,
+'HangulJamo'                            =>  29,
+'Ethiopic'                              =>  30,
+'Cherokee'                              =>  31,
+'UnifiedCanadianAboriginalSyllabics'    =>  32,
+'Ogham'                                 =>  33,
+'Runic'                                 =>  34,
+'Khmer'                                 =>  35,
+'Mongolian'                             =>  36,
+'LatinExtendedAdditional'               =>  37,
+'GreekExtended'                         =>  38,
+'GeneralPunctuation'                    =>  39,
+'SuperscriptsandSubscripts'             =>  40,
+'CurrencySymbols'                       =>  41,
+'CombiningMarksforSymbols'              =>  42,
+'LetterlikeSymbols'                     =>  43,
+'NumberForms'                           =>  44,
+'Arrows'                                =>  45,
+'MathematicalOperators'                 =>  46,
+'MiscellaneousTechnical'                =>  47,
+'ControlPictures'                       =>  48,
+'OpticalCharacterRecognition'           =>  49,
+'EnclosedAlphanumerics'                 =>  50,
+'BoxDrawing'                            =>  51,
+'BlockElements'                         =>  52,
+'GeometricShapes'                       =>  53,
+'MiscellaneousSymbols'                  =>  54,
+'Dingbats'                              =>  55,
+'BraillePatterns'                       =>  56,
+'CJKRadicalsSupplement'                 =>  57,
+'KangxiRadicals'                        =>  58,
+'IdeographicDescriptionCharacters'      =>  59,
+'CJKSymbolsandPunctuation'              =>  60,
+'Hiragana'                              =>  61,
+'Katakana'                              =>  62,
+'Bopomofo'                              =>  63,
+'HangulCompatibilityJamo'               =>  64,
+'Kanbun'                                =>  65,
+'BopomofoExtended'                      =>  66,
+'EnclosedCJKLettersandMonths'           =>  67,
+'CJKCompatibility'                      =>  68,
+'CJKUnifiedIdeographsExtensionA'        =>  69,
+'CJKUnifiedIdeographs'                  =>  70,
+'YiSyllables'                           =>  71,
+'YiRadicals'                            =>  72,
+'HangulSyllables'                       =>  73,
+'HighSurrogates'                        =>  74,
+'HighPrivateUseSurrogates'              =>  75,
+'LowSurrogates'                         =>  76,
+'PrivateUse'                            =>  77,
+'CJKCompatibilityIdeographs'            =>  78,
+'AlphabeticPresentationForms'           =>  79,
+'ArabicPresentationFormsA'              =>  80,
+'CombiningHalfMarks'                    =>  81,
+'CJKCompatibilityForms'                 =>  82,
+'SmallFormVariants'                     =>  83,
+'ArabicPresentationFormsB'              =>  84,
+'Specials'                              =>  85,
+'HalfwidthandFullwidthForms'            =>  86,
+'OldItalic'                             =>  87,
+'Gothic'                                =>  88,
+'Deseret'                               =>  89,
+'ByzantineMusicalSymbols'               =>  90,
+'MusicalSymbols'                        =>  91,
+'MathematicalAlphanumericSymbols'       =>  92,
+'CJKUnifiedIdeographsExtensionB'        =>  93,
+'CJKCompatibilityIdeographsSupplement'  =>  94,
+'Tags'                                  =>  95,
 );

diff --git a/lib/unicode/mktables.PL b/lib/unicode/mktables.PL
index 68578b9..70ed122 100755 (executable)
--- a/lib/unicode/mktables.PL
+++ b/lib/unicode/mktables.PL
@@ -324,8 +324,8 @@ print INID <<EOH;
 EOH
 
 # Order doesn't matter but let's prettyprint anyway.
-foreach my $in (sort { $InId{$a} cmp $InId{$b} } keys %InId) {
-    print INID "'$in' => $InId{$in},\n";
+foreach my $in (sort { $InId{$a} <=> $InId{$b} } keys %InId) {
+    printf INID "%-40s => %2d,\n", "'$in'", $InId{$in};
 }
 
 print INID ");\n";

diff --git a/lib/utf8_heavy.pl b/lib/utf8_heavy.pl
index 5637d12..ab2e15d 100644 (file)
--- a/lib/utf8_heavy.pl
+++ b/lib/utf8_heavy.pl
@@ -38,7 +38,7 @@ sub SWASHNEW {
        || do "$file.pl"
        || do "$encoding/$file.pl"
        || do "$encoding/Is/${type}.pl"
-       || croak("Can't find $encoding character property definition via $caller->$type or $file.pl");
+       || croak("Can't find $encoding character property \"$type\"");
 
     $| = 1;
 

diff --git a/pod/perldiag.pod b/pod/perldiag.pod
index 8d40822..a2614c1 100644 (file)
--- a/pod/perldiag.pod
+++ b/pod/perldiag.pod
@@ -628,6 +628,13 @@ found in the PATH did not have correct permissions.
 (F) A string of a form C<CORE::word> was given to prototype(), but there
 is no builtin with the name C<word>.
 
+=item Can't find %s character property "%s"
+
+(F) You used C<\p{}> or C<\P{}> but the character property by that name
+could not be find.  Maybe you mispelled the name of the property
+(remember that the names of character properties consist only of
+alphanumeric characters), or maybe you forgot the C<Is> or C<In> prefix?
+
 =item Can't find label %s
 
 (F) You said to goto a label that isn't mentioned anywhere that it's