From 7f7d3e8521ec2dd06ee5105c91621451a03b9df4 Mon Sep 17 00:00:00 2001 From: Philip Hazel Date: Wed, 12 Jan 2022 15:30:22 +0000 Subject: [PATCH] Documentation update for binary property support --- doc/html/pcre2pattern.html | 236 +++++++------------------------ doc/html/pcre2syntax.html | 282 +++++++++---------------------------- doc/html/pcre2test.html | 18 ++- doc/pcre2.txt | 228 +++++++++++------------------- doc/pcre2pattern.3 | 239 +++++++------------------------ doc/pcre2syntax.3 | 190 +++---------------------- doc/pcre2test.txt | 16 ++- 7 files changed, 292 insertions(+), 917 deletions(-) diff --git a/doc/html/pcre2pattern.html b/doc/html/pcre2pattern.html index 8007630..d3047be 100644 --- a/doc/html/pcre2pattern.html +++ b/doc/html/pcre2pattern.html @@ -776,8 +776,17 @@ can be used in any mode, though in 8-bit and 16-bit non-UTF modes these sequences are of course limited to testing characters whose code points are less than U+0100 and U+10000, respectively. In 32-bit non-UTF mode, code points greater than 0x10ffff (the Unicode limit) may be encountered. These are all -treated as being in the Unknown script and with an unassigned type. The extra -escape sequences are: +treated as being in the Unknown script and with an unassigned type. +

+

+Matching characters by Unicode property is not fast, because PCRE2 has to do a +multistage table lookup in order to find a character's property. That is why +the traditional escape sequences such as \d and \w do not use Unicode +properties in PCRE2 by default, though you can make them do so by setting the +PCRE2_UCP option or by starting the pattern with (*UCP). +

+

+The extra escape sequences that provide property support are: 

   \p{xx}   a character with the xx property
   \P{xx}   a character without the xx property
@@ -787,17 +796,20 @@ The property names represented by xx above are not case-sensitive, and in
 accordance with Unicode's "loose matching" rules, spaces, hyphens, and
 underscores are ignored. There is support for Unicode script names, Unicode
 general category properties, "Any", which matches any character (including
-newline), Bidi_Control, Bidi_Class, and some special PCRE2 properties
-(described
+newline), Bidi_Class, a number of binary (yes/no) properties, and some special
+PCRE2 properties (described
 below).
-Other Perl properties such as "InMusicalSymbols" are not supported by PCRE2.
-Note that \P{Any} does not match any characters, so always causes a match
-failure.
+Certain other Perl properties such as "InMusicalSymbols" are not supported by
+PCRE2. Note that \P{Any} does not match any characters, so always causes a
+match failure.
 

+

+Script properties for \p and \P
+

 

 There are three different syntax forms for matching a script. Each Unicode
 character has a basic script and, optionally, a list of other scripts ("Script
-Extentions") with which it is commonly used. Using the Adlam script as an
+Extensions") with which it is commonly used. Using the Adlam script as an
 example, \p{sc:Adlam} matches characters whose basic script is Adlam, whereas
 \p{scx:Adlam} matches, in addition, characters that have Adlam in their
 extensions list. The full names "script" and "script extensions" for the
@@ -809,172 +821,17 @@ interpretation at release 5.26 and PCRE2 changed at release 10.40.
 

 Unassigned characters (and in non-UTF 32-bit mode, characters with code points
 greater than 0x10FFFF) are assigned the "Unknown" script. Others that are not
-part of an identified script are lumped together as "Common". The current list
-of script names and their 4-letter abbreviations is:
-

-

-Adlam (Adlm),
-Ahom (Ahom),
-Anatolian_Hieroglyphs (Hluw),
-Arabic (Arab),
-Armenian (Armn),
-Avestan (Avst),
-Balinese (Bali),
-Bamum (Bamu),
-Bassa_Vah (Bass),
-Batak (Batk),
-Bengali (Beng),
-Bhaiksuki (Bhks),
-Bopomofo (Bopo),
-Brahmi (Brah),
-Braille (Brai),
-Buginese (Bugi),
-Buhid (Buhd),
-Canadian_Aboriginal (Cans),
-Carian (Cari),
-Caucasian_Albanian (Aghb),
-Chakma (Cakm),
-Cham (Cham),
-Cherokee (Cher),
-Chorasmian (Chrs),
-Common (Zyyy),
-Coptic (Copt),
-Cuneiform (Xsux),
-Cypriot (Cprt),
-Cypro_Minoan (Cpmn),
-Cyrillic (Cyrl),
-Deseret (Dsrt),
-Devanagari (Deva),
-Dives_Akuru (Diak),
-Dogra (Dogr),
-Duployan (Dupl),
-Egyptian_Hieroglyphs (Egyp),
-Elbasan (Elba),
-Elymaic (Elym),
-Ethiopic (Ethi),
-Georgian (Geor),
-Glagolitic (Glag),
-Gothic (Goth),
-Grantha (Gran),
-Greek (Grek),
-Gujarati (Gujr),
-Gunjala_Gondi (Gong),
-Gurmukhi (Guru),
-Han (Hani),
-Hangul (Hang),
-Hanifi_Rohingya (Rohg),
-Hanunoo (Hano),
-Hatran (Hatr),
-Hebrew (Hebr),
-Hiragana (Hira),
-Imperial_Aramaic (Armi),
-Inherited (Zinh),
-Inscriptional_Pahlavi (Phli),
-Inscriptional_Parthian (Prti),
-Javanese (Java),
-Kaithi (Kthi),
-Kannada (Knda),
-Katakana (Kana),
-Kayah_Li (Kali),
-Kharoshthi (Khar),
-Khitan_Small_Script (Kits),
-Khmer (Khmr),
-Khojki (Khoj),
-Khudawadi (Sind),
-Lao (Laoo),
-Latin (Latn),
-Lepcha (Lepc),
-Limbu (Limb),
-Linear_A (Lina),
-Linear_B (Linb),
-Lisu (Lisu),
-Lycian (Lyci),
-Lydian (Lydi),
-Mahajani (Majh),
-Makasar (Maka),
-Malayalam (Mlym),
-Mandaic (Mand),
-Manichaean (Mani),
-Marchen (Marc),
-Masaram_Gondi (Gonm),
-Medefaidrin (Medf),
-Meetei_Mayek (Mtei),
-Mende_Kikakui (Mend),
-Meroitic_Cursive (Merc),
-Meroitic_Hieroglyphs (Mero),
-Miao (Miao),
-Modi (Modi),
-Mongolian (Mong),
-Mro (Mroo),
-Multani (Mult),
-Myanmar (Mymr),
-Nabataean (Nbar),
-Nandinagari (Nand),
-New_Tai_Lue (Talu),
-Newa (Newa),
-Nko (Nkoo),
-Nushu (Nshu),
-Nyiakeng_Puachue_Hmong (Hmnp),
-Ogham (Ogam),
-Ol_Chiki (Olck),
-Old_Hungarian (Hung),
-Old_Italic (Olck),
-Old_North_Arabian (Narb),
-Old_Permic (Perm),
-Old_Persian (Orkh),
-Old_Sogdian (Sogo),
-Old_South_Arabian (Sarb),
-Old_Turkic (Orkh),
-Old_Uyghur (Ougr),
-Oriya (Orya),
-Osage (Osge),
-Osmanya (Osma),
-Pahawh_Hmong (Hmng),
-Palmyrene (Palm),
-Pau_Cin_Hau (Pauc),
-Phags_Pa (Phag),
-Phoenician (Phnx),
-Psalter_Pahlavi (Phli),
-Rejang (Rjng),
-Runic (Runr),
-Samaritan (Samr),
-Saurashtra (Saur),
-Sharada (Shrd),
-Shavian (Shaw),
-Siddham (Sidd),
-SignWriting (Sgnw),
-Sinhala (Sinh),
-Sogdian (Sogd),
-Sora_Sompeng (Sora),
-Soyombo (Soyo),
-Sundanese (Sund),
-Syloti_Nagri (Sylo),
-Syriac (Syrc),
-Tagalog (Tglg),
-Tagbanwa (Tagb),
-Tai_Le (Tale),
-Tai_Tham (Lana),
-Tai_Viet (Tavt),
-Takri (Takr),
-Tamil (Taml),
-Tangsa (Tngs),
-Tangut (Tang),
-Telugu (Telu),
-Thaana (Thaa),
-Thai (Thai),
-Tibetan (Tibt),
-Tifinagh (Tfng),
-Tirhuta (Tirh),
-Toto (Toto),
-Ugaritic (Ugar),
-Vai (Vaii),
-Vithkuqi (Vith),
-Wancho (Wcho),
-Warang_Citi (Wara),
-Yezidi (Yezi),
-Yi (Yiii),
-Zanabazar_Square (Zanb).
+part of an identified script are lumped together as "Common". The current list 
+of recognized script names and their 4-character abbreviations can be obtained 
+by running this command:
+
+  pcre2test -LS
+
+

 

+

+The general category property for \p and \P
+

 

 Each character has exactly one Unicode general category property, specified by
 a two-letter abbreviation. For compatibility with Perl, negation can be
@@ -1065,22 +922,23 @@ Specifying caseless matching does not affect these escape sequences. For
 example, \p{Lu} always matches only upper case letters. This is different from
 the behaviour of current versions of Perl.
 

-

-Matching characters by Unicode property is not fast, because PCRE2 has to do a
-multistage table lookup in order to find a character's property. That is why
-the traditional escape sequences such as \d and \w do not use Unicode
-properties in PCRE2 by default, though you can make them do so by setting the
-PCRE2_UCP option or by starting the pattern with (*UCP).
-

 

-Bi-directional properties for \p and \P
+Binary (yes/no) properties for \p and \P
+

+

+Unicode defines a number of binary properties, that is, properties whose only
+values are true or false. You can obtain a list of those that are recognized by
+\p and \P, along with their abbreviations, by running this command:
+
+  pcre2test -LP
+
+

+

+

+The Bidi_Class property for \p and \P
 

 

-Two properties relating to bi-directional text (each with a shorter synonym)
-are supported:
 
-  \p{Bidi_Control}         matches a Bidi control character
-  \p{Bidi_C}               matches a Bidi control character
   \p{Bidi_Class:<class>}   matches a character with the given class
   \p{BC:<class>}           matches a character with the given class
 

@@ -1110,8 +968,8 @@ The recognized classes are:
   S           segment separator
   WS          which space
-For Bidi_Class, an equals sign may be used instead of a colon. The class names -are case-insensitive; only the short names listed above are recognized. +An equals sign may be used instead of a colon. The class names are +case-insensitive; only the short names listed above are recognized.


Extended grapheme clusters @@ -3908,9 +3766,9 @@ Cambridge, England.


REVISION

-Last updated: 28 December 2021 +Last updated: 12 January 2022
-Copyright © 1997-2021 University of Cambridge. +Copyright © 1997-2022 University of Cambridge.

Return to the PCRE2 index page. diff --git a/doc/html/pcre2syntax.html b/doc/html/pcre2syntax.html index bbbac32..b0eb96d 100644 --- a/doc/html/pcre2syntax.html +++ b/doc/html/pcre2syntax.html @@ -19,30 +19,31 @@ please consult the man page, in case the conversion went wrong.

  • CHARACTER TYPES
  • GENERAL CATEGORY PROPERTIES FOR \p and \P
  • PCRE2 SPECIAL CATEGORY PROPERTIES FOR \p and \P -
  • SCRIPT MATCHING WITH \p AND \P -
  • BIDI_PROPERTIES FOR \p AND \P -
  • CHARACTER CLASSES -
  • QUANTIFIERS -
  • ANCHORS AND SIMPLE ASSERTIONS -
  • REPORTED MATCH POINT SETTING -
  • ALTERNATION -
  • CAPTURING -
  • ATOMIC GROUPS -
  • COMMENT -
  • OPTION SETTING -
  • NEWLINE CONVENTION -
  • WHAT \R MATCHES -
  • LOOKAHEAD AND LOOKBEHIND ASSERTIONS -
  • NON-ATOMIC LOOKAROUND ASSERTIONS -
  • SCRIPT RUNS -
  • BACKREFERENCES -
  • SUBROUTINE REFERENCES (POSSIBLY RECURSIVE) -
  • CONDITIONAL PATTERNS -
  • BACKTRACKING CONTROL -
  • CALLOUTS -
  • SEE ALSO -
  • AUTHOR -
  • REVISION +
  • BINARY PROPERTIES FOR \p AND \P +
  • SCRIPT MATCHING WITH \p AND \P +
  • THE BIDI_CLASS PROPERTY FOR \p AND \P +
  • CHARACTER CLASSES +
  • QUANTIFIERS +
  • ANCHORS AND SIMPLE ASSERTIONS +
  • REPORTED MATCH POINT SETTING +
  • ALTERNATION +
  • CAPTURING +
  • ATOMIC GROUPS +
  • COMMENT +
  • OPTION SETTING +
  • NEWLINE CONVENTION +
  • WHAT \R MATCHES +
  • LOOKAHEAD AND LOOKBEHIND ASSERTIONS +
  • NON-ATOMIC LOOKAROUND ASSERTIONS +
  • SCRIPT RUNS +
  • BACKREFERENCES +
  • SUBROUTINE REFERENCES (POSSIBLY RECURSIVE) +
  • CONDITIONAL PATTERNS +
  • BACKTRACKING CONTROL +
  • CALLOUTS +
  • SEE ALSO +
  • AUTHOR +
  • REVISION
    PCRE2 REGULAR EXPRESSION SYNTAX SUMMARY

    @@ -205,180 +206,27 @@ matching" rules. Perl and POSIX space are now the same. Perl added VT to its space character set at release 5.18.

    -
    SCRIPT MATCHING WITH \p AND \P
    +
    BINARY PROPERTIES FOR \p AND \P

    -The following script names and their 4-letter abbreviations are recognized in +Unicode defines a number of binary properties, that is, properties whose only +values are true or false. You can obtain a list of those that are recognized by +\p and \P, along with their abbreviations, by running this command: +

    +  pcre2test -LP
+
    +

    +
    SCRIPT MATCHING WITH \p AND \P
    +

    +Many script names and their 4-letter abbreviations are recognized in \p{sc:...} or \p{scx:...} items, or on their own with \p (and also \P of -course): +course). You can obtain a list of these scripts by running this command: +

    +  pcre2test -LS
+

    -

    -Adlam (Adlm), -Ahom (Ahom), -Anatolian_Hieroglyphs (Hluw), -Arabic (Arab), -Armenian (Armn), -Avestan (Avst), -Balinese (Bali), -Bamum (Bamu), -Bassa_Vah (Bass), -Batak (Batk), -Bengali (Beng), -Bhaiksuki (Bhks), -Bopomofo (Bopo), -Brahmi (Brah), -Braille (Brai), -Buginese (Bugi), -Buhid (Buhd), -Canadian_Aboriginal (Cans), -Carian (Cari), -Caucasian_Albanian (Aghb), -Chakma (Cakm), -Cham (Cham), -Cherokee (Cher), -Chorasmian (Chrs), -Common (Zyyy), -Coptic (Copt), -Cuneiform (Xsux), -Cypriot (Cprt), -Cypro_Minoan (Cpmn), -Cyrillic (Cyrl), -Deseret (Dsrt), -Devanagari (Deva), -Dives_Akuru (Diak), -Dogra (Dogr), -Duployan (Dupl), -Egyptian_Hieroglyphs (Egyp), -Elbasan (Elba), -Elymaic (Elym), -Ethiopic (Ethi), -Georgian (Geor), -Glagolitic (Glag), -Gothic (Goth), -Grantha (Gran), -Greek (Grek), -Gujarati (Gujr), -Gunjala_Gondi (Gong), -Gurmukhi (Guru), -Han (Hani), -Hangul (Hang), -Hanifi_Rohingya (Rohg), -Hanunoo (Hano), -Hatran (Hatr), -Hebrew (Hebr), -Hiragana (Hira), -Imperial_Aramaic (Armi), -Inherited (Zinh), -Inscriptional_Pahlavi (Phli), -Inscriptional_Parthian (Prti), -Javanese (Java), -Kaithi (Kthi), -Kannada (Knda), -Katakana (Kana), -Kayah_Li (Kali), -Kharoshthi (Khar), -Khitan_Small_Script (Kits), -Khmer (Khmr), -Khojki (Khoj), -Khudawadi (Sind), -Lao (Laoo), -Latin (Latn), -Lepcha (Lepc), -Limbu (Limb), -Linear_A (Lina), -Linear_B (Linb), -Lisu (Lisu), -Lycian (Lyci), -Lydian (Lydi), -Mahajani (Majh), -Makasar (Maka), -Malayalam (Mlym), -Mandaic (Mand), -Manichaean (Mani), -Marchen (Marc), -Masaram_Gondi (Gonm), -Medefaidrin (Medf), -Meetei_Mayek (Mtei), -Mende_Kikakui (Mend), -Meroitic_Cursive (Merc), -Meroitic_Hieroglyphs (Mero), -Miao (Miao), -Modi (Modi), -Mongolian (Mong), -Mro (Mroo), -Multani (Mult), -Myanmar (Mymr), -Nabataean (Nbar), -Nandinagari (Nand), -New_Tai_Lue (Talu), -Newa (Newa), -Nko (Nkoo), -Nushu (Nshu), -Nyiakeng_Puachue_Hmong (Hmnp), -Ogham (Ogam), -Ol_Chiki (Olck), -Old_Hungarian (Hung), -Old_Italic (Olck), -Old_North_Arabian (Narb), -Old_Permic (Perm), -Old_Persian (Orkh), -Old_Sogdian (Sogo), -Old_South_Arabian (Sarb), -Old_Turkic (Orkh), -Old_Uyghur (Ougr), -Oriya (Orya), -Osage (Osge), -Osmanya (Osma), -Pahawh_Hmong (Hmng), -Palmyrene (Palm), -Pau_Cin_Hau (Pauc), -Phags_Pa (Phag), -Phoenician (Phnx), -Psalter_Pahlavi (Phli), -Rejang (Rjng), -Runic (Runr), -Samaritan (Samr), -Saurashtra (Saur), -Sharada (Shrd), -Shavian (Shaw), -Siddham (Sidd), -SignWriting (Sgnw), -Sinhala (Sinh), -Sogdian (Sogd), -Sora_Sompeng (Sora), -Soyombo (Soyo), -Sundanese (Sund), -Syloti_Nagri (Sylo), -Syriac (Syrc), -Tagalog (Tglg), -Tagbanwa (Tagb), -Tai_Le (Tale), -Tai_Tham (Lana), -Tai_Viet (Tavt), -Takri (Takr), -Tamil (Taml), -Tangsa (Tngs), -Tangut (Tang), -Telugu (Telu), -Thaana (Thaa), -Thai (Thai), -Tibetan (Tibt), -Tifinagh (Tfng), -Tirhuta (Tirh), -Toto (Toto), -Ugaritic (Ugar), -Vai (Vaii), -Vithkuqi (Vith), -Wancho (Wcho), -Warang_Citi (Wara), -Yezidi (Yezi), -Yi (Yiii), -Zanabazar_Square (Zanb). -

    -
    BIDI_PROPERTIES FOR \p AND \P
    +
    THE BIDI_CLASS PROPERTY FOR \p AND \P

    -  \p{Bidi_Control}         matches a Bidi control character
-  \p{Bidi_C}               matches a Bidi control character
   \p{Bidi_Class:<class>}   matches a character with the given class
   \p{BC:<class>}           matches a character with the given class
    @@ -409,7 +257,7 @@ The recognized classes are: WS which space

    -
    CHARACTER CLASSES
    +
    CHARACTER CLASSES

       [...]       positive character class
@@ -437,7 +285,7 @@ In PCRE2, POSIX character set names recognize only ASCII characters by default,
 but some of them use Unicode properties if PCRE2_UCP is set. You can use
 \Q...\E inside a character class.
 
    
-
    QUANTIFIERS
    
+
    QUANTIFIERS
    
 
    
 
       ?           0 or 1, greedy
@@ -458,7 +306,7 @@ but some of them use Unicode properties if PCRE2_UCP is set. You can use
   {n,}?       n or more, lazy
 
    
 
    
-
    ANCHORS AND SIMPLE ASSERTIONS
    
+
    ANCHORS AND SIMPLE ASSERTIONS
    
 
    
 
       \b          word boundary
@@ -476,7 +324,7 @@ but some of them use Unicode properties if PCRE2_UCP is set. You can use
   \G          first matching position in subject
 
    
 
    
-
    REPORTED MATCH POINT SETTING
    
+
    REPORTED MATCH POINT SETTING
    
 
    
 
       \K          set reported start of match
@@ -486,13 +334,13 @@ for compatibility with Perl. However, if the PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK
 option is set, the previous behaviour is re-enabled. When this option is set,
 \K is honoured in positive assertions, but ignored in negative ones.
 
    
-
    ALTERNATION
    
+
    ALTERNATION
    
 
    
 
       expr|expr|expr...
 
    
 
    
-
    CAPTURING
    
+
    CAPTURING
    
 
    
 
       (...)           capture group
@@ -507,20 +355,20 @@ In non-UTF modes, names may contain underscores and ASCII letters and digits;
 in UTF modes, any Unicode letters and Unicode decimal digits are permitted. In
 both cases, a name must not start with a digit.
 
    
-
    ATOMIC GROUPS
    
+
    ATOMIC GROUPS
    
 
    
 
       (?>...)         atomic non-capture group
   (*atomic:...)   atomic non-capture group
 
    
 
    
-
    COMMENT
    
+
    COMMENT
    
 
    
 
       (?#....)        comment (not nestable)
 
    
 
    
-
    OPTION SETTING
    
+
    OPTION SETTING
    
 
    
 Changes of these options within a group are automatically cancelled at the end
 of the group.
@@ -565,7 +413,7 @@ not increase them. LIMIT_RECURSION is an obsolete synonym for LIMIT_DEPTH. The
 application can lock out the use of (*UTF) and (*UCP) by setting the
 PCRE2_NEVER_UTF or PCRE2_NEVER_UCP options, respectively, at compile time.
 
    
-
    NEWLINE CONVENTION
    
+
    NEWLINE CONVENTION
    
 
    
 These are recognized only at the very start of the pattern or after option
 settings with a similar syntax.
@@ -578,7 +426,7 @@ settings with a similar syntax.
   (*NUL)          the NUL character (binary zero)
 
    
 
    
-
    WHAT \R MATCHES
    
+
    WHAT \R MATCHES
    
 
    
 These are recognized only at the very start of the pattern or after option
 setting with a similar syntax.
@@ -587,7 +435,7 @@ setting with a similar syntax.
   (*BSR_UNICODE)  any Unicode newline sequence
 
    
 
    
-
    LOOKAHEAD AND LOOKBEHIND ASSERTIONS
    
+
    LOOKAHEAD AND LOOKBEHIND ASSERTIONS
    
 
    
 
       (?=...)                     )
@@ -608,7 +456,7 @@ setting with a similar syntax.
 
    
 Each top-level branch of a lookbehind must be of a fixed length.
 
    
-
    NON-ATOMIC LOOKAROUND ASSERTIONS
    
+
    NON-ATOMIC LOOKAROUND ASSERTIONS
    
 
    
 These assertions are specific to PCRE2 and are not Perl-compatible.
 
    @@ -621,7 +469,7 @@ These assertions are specific to PCRE2 and are not Perl-compatible.
   (*non_atomic_positive_lookbehind:...)  )
 
    
 
    
-
    SCRIPT RUNS
    
+
    SCRIPT RUNS
    
 
    
 
       (*script_run:...)           ) script run, can be backtracked into
@@ -631,7 +479,7 @@ These assertions are specific to PCRE2 and are not Perl-compatible.
   (*asr:...)                  )
 
    
 
    
-
    BACKREFERENCES
    
+
    BACKREFERENCES
    
 
    
 
       \n              reference by number (can be ambiguous)
@@ -648,7 +496,7 @@ These assertions are specific to PCRE2 and are not Perl-compatible.
   (?P=name)       reference by name (Python)
 
    
 
    
-
    SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)
    
+
    SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)
    
 
    
 
       (?R)            recurse whole pattern
@@ -667,7 +515,7 @@ These assertions are specific to PCRE2 and are not Perl-compatible.
   \g'-n'          call subroutine by relative number (PCRE2 extension)
 
    
 
    
-
    CONDITIONAL PATTERNS
    
+
    CONDITIONAL PATTERNS
    
 
    
 
       (?(condition)yes-pattern)
@@ -690,7 +538,7 @@ Note the ambiguity of (?(R) and (?(Rn) which might be named reference
 conditions or recursion tests. Such a condition is interpreted as a reference
 condition if the relevant named group exists.
 
    
-
    BACKTRACKING CONTROL
    
+
    BACKTRACKING CONTROL
    
 
    
 All backtracking control verbs may be in the form (*VERB:NAME). For (*MARK) the
 name is mandatory, for the others it is optional. (*SKIP) changes its behaviour
@@ -717,7 +565,7 @@ pattern is not anchored.
 The effect of one of these verbs in a group called as a subroutine is confined
 to the subroutine call.
 
    
-
    CALLOUTS
    
+
    CALLOUTS
    
 
    
 
       (?C)            callout (assumed number 0)
@@ -728,12 +576,12 @@ The allowed string delimiters are ` ' " ^ % # $ (which are the same for the
 start and the end), and the starting delimiter { matched with the ending
 delimiter }. To encode the ending delimiter within the string, double it.
 
    
-
    SEE ALSO
    
+
    SEE ALSO
    
 
    
 pcre2pattern(3), pcre2api(3), pcre2callout(3),
 pcre2matching(3), pcre2(3).
 
    
-
    AUTHOR
    
+
    AUTHOR
    
 
    
 Philip Hazel
 
    
@@ -742,11 +590,11 @@ Retired from University Computing Service
 Cambridge, England.
 
    
 
    
-
    REVISION
    
+
    REVISION
    
 
    
-Last updated: 28 December 2021
+Last updated: 12 January 2022
 
    
-Copyright © 1997-2021 University of Cambridge.
+Copyright © 1997-2022 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/doc/html/pcre2test.html b/doc/html/pcre2test.html
index 7f72779..54e2c6a 100644
--- a/doc/html/pcre2test.html
+++ b/doc/html/pcre2test.html
@@ -253,7 +253,19 @@ available, and the use of JIT for matching is verified.
 -LM
 List modifiers: write a list of available pattern and subject modifiers to the
 standard output, then exit with zero exit code. All other options are ignored.
-If both -C and -LM are present, whichever is first is recognized.
+If both -C and any -Lx options are present, whichever is first is recognized.
+
    
+
    
+-LP
+List properties: write a list of recognized Unicode properties to the standard
+output, then exit with zero exit code. All other options are ignored. If both
+-C and any -Lx options are present, whichever is first is recognized.
+
    
+
    
+-LS
+List scripts: write a list of recogized Unicode script names to the standard
+output, then exit with zero exit code. All other options are ignored. If both
+-C and any -Lx options are present, whichever is first is recognized.
 
    
 
    
 -pattern modifier-list
@@ -2129,9 +2141,9 @@ Cambridge, England.
 
    
 
    REVISION
    
 
    
-Last updated: 28 November 2021
+Last updated: 12 January 2022
 
    
-Copyright © 1997-2021 University of Cambridge.
+Copyright © 1997-2022 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/doc/pcre2.txt b/doc/pcre2.txt
index 3f79c39..6598503 100644
--- a/doc/pcre2.txt
+++ b/doc/pcre2.txt
@@ -6889,8 +6889,16 @@ BACKSLASH
        ters  whose code points are less than U+0100 and U+10000, respectively.
        In 32-bit non-UTF mode, code points greater than 0x10ffff (the  Unicode
        limit)  may  be  encountered. These are all treated as being in the Un-
-       known script and with an unassigned type. The  extra  escape  sequences
-       are:
+       known script and with an unassigned type.
+
+       Matching characters by Unicode property is not fast, because PCRE2  has
+       to  do  a  multistage table lookup in order to find a character's prop-
+       erty. That is why the traditional escape sequences such as \d and \w do
+       not  use  Unicode  properties  in PCRE2 by default, though you can make
+       them do so by setting the PCRE2_UCP option or by starting  the  pattern
+       with (*UCP).
+
+       The extra escape sequences that provide property support are:
 
          \p{xx}   a character with the xx property
          \P{xx}   a character without the xx property
@@ -6900,71 +6908,36 @@ BACKSLASH
        in accordance with Unicode's "loose matching" rules,  spaces,  hyphens,
        and underscores are ignored. There is support for Unicode script names,
        Unicode general category properties, "Any", which matches any character
-       (including  newline),  Bidi_Control, Bidi_Class, and some special PCRE2
-       properties (described below).  Other Perl properties such  as  "InMusi-
-       calSymbols"  are  not  supported  by PCRE2.  Note that \P{Any} does not
-       match any characters, so always causes a match failure.
+       (including  newline),  Bidi_Class,  a number of binary (yes/no) proper-
+       ties, and some special PCRE2  properties  (described  below).   Certain
+       other  Perl  properties such as "InMusicalSymbols" are not supported by
+       PCRE2. Note that \P{Any} does  not  match  any  characters,  so  always
+       causes a match failure.
+
+   Script properties for \p and \P
 
        There are three different syntax forms for matching a script. Each Uni-
-       code  character  has  a  basic  script and, optionally, a list of other
-       scripts ("Script Extentions") with which it is commonly used. Using the
+       code character has a basic script and,  optionally,  a  list  of  other
+       scripts ("Script Extensions") with which it is commonly used. Using the
        Adlam script as an example, \p{sc:Adlam} matches characters whose basic
        script is Adlam, whereas \p{scx:Adlam} matches, in addition, characters
-       that  have  Adlam in their extensions list. The full names "script" and
+       that have Adlam in their extensions list. The full names  "script"  and
        "script extensions" for the property types are recognized, and a equals
-       sign  is an alternative to the colon. If a script name is given without
-       a property type, for example, \p{Adlam}, it is  treated  as  \p{scx:Ad-
-       lam}.  Perl  changed  to  this interpretation at release 5.26 and PCRE2
+       sign is an alternative to the colon. If a script name is given  without
+       a  property  type,  for example, \p{Adlam}, it is treated as \p{scx:Ad-
+       lam}. Perl changed to this interpretation at  release  5.26  and  PCRE2
        changed at release 10.40.
 
        Unassigned characters (and in non-UTF 32-bit mode, characters with code
        points greater than 0x10FFFF) are assigned the "Unknown" script. Others
-       that are not part of an identified script are lumped together as  "Com-
-       mon". The current list of script names and their 4-letter abbreviations
-       is:
+       that  are not part of an identified script are lumped together as "Com-
+       mon". The current list of recognized script names and their 4-character
+       abbreviations can be obtained by running this command:
 
-       Adlam (Adlm), Ahom (Ahom), Anatolian_Hieroglyphs (Hluw), Arabic (Arab),
-       Armenian   (Armn),  Avestan  (Avst),  Balinese  (Bali),  Bamum  (Bamu),
-       Bassa_Vah (Bass), Batak (Batk), Bengali (Beng), Bhaiksuki (Bhks), Bopo-
-       mofo  (Bopo),  Brahmi  (Brah),  Braille  (Brai), Buginese (Bugi), Buhid
-       (Buhd), Canadian_Aboriginal (Cans), Carian  (Cari),  Caucasian_Albanian
-       (Aghb), Chakma (Cakm), Cham (Cham), Cherokee (Cher), Chorasmian (Chrs),
-       Common  (Zyyy),  Coptic  (Copt),  Cuneiform  (Xsux),  Cypriot   (Cprt),
-       Cypro_Minoan   (Cpmn),  Cyrillic  (Cyrl),  Deseret  (Dsrt),  Devanagari
-       (Deva), Dives_Akuru (Diak), Dogra (Dogr), Duployan (Dupl), Egyptian_Hi-
-       eroglyphs  (Egyp),  Elbasan  (Elba),  Elymaic  (Elym), Ethiopic (Ethi),
-       Georgian (Geor), Glagolitic  (Glag),  Gothic  (Goth),  Grantha  (Gran),
-       Greek  (Grek),  Gujarati (Gujr), Gunjala_Gondi (Gong), Gurmukhi (Guru),
-       Han (Hani), Hangul (Hang), Hanifi_Rohingya (Rohg), Hanunoo (Hano),  Ha-
-       tran  (Hatr),  Hebrew (Hebr), Hiragana (Hira), Imperial_Aramaic (Armi),
-       Inherited (Zinh), Inscriptional_Pahlavi (Phli),  Inscriptional_Parthian
-       (Prti),  Javanese  (Java),  Kaithi  (Kthi),  Kannada  (Knda),  Katakana
-       (Kana), Kayah_Li (Kali), Kharoshthi (Khar), Khitan_Small_Script (Kits),
-       Khmer  (Khmr),  Khojki  (Khoj),  Khudawadi  (Sind),  Lao  (Laoo), Latin
-       (Latn), Lepcha (Lepc), Limbu (Limb), Linear_A (Lina), Linear_B  (Linb),
-       Lisu  (Lisu),  Lycian  (Lyci),  Lydian (Lydi), Mahajani (Majh), Makasar
-       (Maka), Malayalam (Mlym), Mandaic (Mand),  Manichaean  (Mani),  Marchen
-       (Marc),  Masaram_Gondi (Gonm), Medefaidrin (Medf), Meetei_Mayek (Mtei),
-       Mende_Kikakui  (Mend),  Meroitic_Cursive  (Merc),  Meroitic_Hieroglyphs
-       (Mero), Miao (Miao), Modi (Modi), Mongolian (Mong), Mro (Mroo), Multani
-       (Mult),  Myanmar  (Mymr),   Nabataean   (Nbar),   Nandinagari   (Nand),
-       New_Tai_Lue  (Talu),  Newa  (Newa),  Nko  (Nkoo),  Nushu (Nshu), Nyiak-
-       eng_Puachue_Hmong (Hmnp), Ogham (Ogam), Ol_Chiki (Olck),  Old_Hungarian
-       (Hung), Old_Italic (Olck), Old_North_Arabian (Narb), Old_Permic (Perm),
-       Old_Persian  (Orkh),  Old_Sogdian  (Sogo),  Old_South_Arabian   (Sarb),
-       Old_Turkic  (Orkh),  Old_Uyghur (Ougr), Oriya (Orya), Osage (Osge), Os-
-       manya  (Osma),  Pahawh_Hmong  (Hmng),  Palmyrene  (Palm),   Pau_Cin_Hau
-       (Pauc), Phags_Pa (Phag), Phoenician (Phnx), Psalter_Pahlavi (Phli), Re-
-       jang (Rjng), Runic (Runr), Samaritan (Samr), Saurashtra (Saur), Sharada
-       (Shrd),  Shavian  (Shaw),  Siddham  (Sidd), SignWriting (Sgnw), Sinhala
-       (Sinh), Sogdian (Sogd), Sora_Sompeng (Sora), Soyombo (Soyo),  Sundanese
-       (Sund),  Syloti_Nagri  (Sylo),  Syriac (Syrc), Tagalog (Tglg), Tagbanwa
-       (Tagb), Tai_Le (Tale), Tai_Tham (Lana), Tai_Viet (Tavt), Takri  (Takr),
-       Tamil  (Taml),  Tangsa  (Tngs),  Tangut  (Tang),  Telugu (Telu), Thaana
-       (Thaa), Thai (Thai), Tibetan (Tibt), Tifinagh (Tfng),  Tirhuta  (Tirh),
-       Toto  (Toto),  Ugaritic  (Ugar),  Vai  (Vaii),  Vithkuqi (Vith), Wancho
-       (Wcho), Warang_Citi (Wara), Yezidi (Yezi), Yi (Yiii),  Zanabazar_Square
-       (Zanb).
+         pcre2test -LS
+
+
+   The general category property for \p and \P
 
        Each character has exactly one Unicode general category property, spec-
        ified by a two-letter abbreviation. For compatibility with Perl,  nega-
@@ -7050,20 +7023,18 @@ BACKSLASH
        For  example,  \p{Lu}  always  matches only upper case letters. This is
        different from the behaviour of current versions of Perl.
 
-       Matching characters by Unicode property is not fast, because PCRE2  has
-       to  do  a  multistage table lookup in order to find a character's prop-
-       erty. That is why the traditional escape sequences such as \d and \w do
-       not  use  Unicode  properties  in PCRE2 by default, though you can make
-       them do so by setting the PCRE2_UCP option or by starting  the  pattern
-       with (*UCP).
+   Binary (yes/no) properties for \p and \P
 
-   Bi-directional properties for \p and \P
+       Unicode defines a number of  binary  properties,  that  is,  properties
+       whose  only  values  are  true or false. You can obtain a list of those
+       that are recognized by \p and \P, along with  their  abbreviations,  by
+       running this command:
 
-       Two  properties  relating  to  bi-directional text (each with a shorter
-       synonym) are supported:
+         pcre2test -LP
+
+
+   The Bidi_Class property for \p and \P
 
-         \p{Bidi_Control}         matches a Bidi control character
-         \p{Bidi_C}               matches a Bidi control character
          \p{Bidi_Class:}   matches a character with the given class
          \p{BC:}           matches a character with the given class
 
@@ -7093,9 +7064,8 @@ BACKSLASH
          S           segment separator
          WS          which space
 
-       For Bidi_Class, an equals sign may be used  instead  of  a  colon.  The
-       class names are case-insensitive; only the short names listed above are
-       recognized.
+       An  equals  sign  may  be  used instead of a colon. The class names are
+       case-insensitive; only the short names listed above are recognized.
 
    Extended grapheme clusters
 
@@ -9725,8 +9695,8 @@ AUTHOR
 
 REVISION
 
-       Last updated: 28 December 2021
-       Copyright (c) 1997-2021 University of Cambridge.
+       Last updated: 12 January 2022
+       Copyright (c) 1997-2022 University of Cambridge.
 ------------------------------------------------------------------------------
  
  
@@ -10739,60 +10709,28 @@ PCRE2 SPECIAL CATEGORY PROPERTIES FOR \p and \P
        acter set at release 5.18.
 
 
+BINARY PROPERTIES FOR \p AND \P
+
+       Unicode  defines  a  number  of  binary properties, that is, properties
+       whose only values are true or false. You can obtain  a  list  of  those
+       that  are  recognized  by \p and \P, along with their abbreviations, by
+       running this command:
+
+         pcre2test -LP
+
+
 SCRIPT MATCHING WITH \p AND \P
 
-       The  following script names and their 4-letter abbreviations are recog-
-       nized in \p{sc:...} or \p{scx:...} items, or on their own with \p  (and
-       also \P of course):
+       Many script names and their 4-letter abbreviations  are  recognized  in
+       \p{sc:...}  or  \p{scx:...} items, or on their own with \p (and also \P
+       of course). You can obtain a list of these scripts by running this com-
+       mand:
 
-       Adlam (Adlm), Ahom (Ahom), Anatolian_Hieroglyphs (Hluw), Arabic (Arab),
-       Armenian  (Armn),  Avestan  (Avst),  Balinese  (Bali),  Bamum   (Bamu),
-       Bassa_Vah (Bass), Batak (Batk), Bengali (Beng), Bhaiksuki (Bhks), Bopo-
-       mofo (Bopo), Brahmi (Brah),  Braille  (Brai),  Buginese  (Bugi),  Buhid
-       (Buhd),  Canadian_Aboriginal  (Cans), Carian (Cari), Caucasian_Albanian
-       (Aghb), Chakma (Cakm), Cham (Cham), Cherokee (Cher), Chorasmian (Chrs),
-       Common   (Zyyy),  Coptic  (Copt),  Cuneiform  (Xsux),  Cypriot  (Cprt),
-       Cypro_Minoan  (Cpmn),  Cyrillic  (Cyrl),  Deseret  (Dsrt),   Devanagari
-       (Deva), Dives_Akuru (Diak), Dogra (Dogr), Duployan (Dupl), Egyptian_Hi-
-       eroglyphs (Egyp), Elbasan  (Elba),  Elymaic  (Elym),  Ethiopic  (Ethi),
-       Georgian  (Geor),  Glagolitic  (Glag),  Gothic  (Goth), Grantha (Gran),
-       Greek (Grek), Gujarati (Gujr), Gunjala_Gondi (Gong),  Gurmukhi  (Guru),
-       Han  (Hani), Hangul (Hang), Hanifi_Rohingya (Rohg), Hanunoo (Hano), Ha-
-       tran (Hatr), Hebrew (Hebr), Hiragana (Hira),  Imperial_Aramaic  (Armi),
-       Inherited  (Zinh), Inscriptional_Pahlavi (Phli), Inscriptional_Parthian
-       (Prti),  Javanese  (Java),  Kaithi  (Kthi),  Kannada  (Knda),  Katakana
-       (Kana), Kayah_Li (Kali), Kharoshthi (Khar), Khitan_Small_Script (Kits),
-       Khmer (Khmr),  Khojki  (Khoj),  Khudawadi  (Sind),  Lao  (Laoo),  Latin
-       (Latn),  Lepcha (Lepc), Limbu (Limb), Linear_A (Lina), Linear_B (Linb),
-       Lisu (Lisu), Lycian (Lyci), Lydian  (Lydi),  Mahajani  (Majh),  Makasar
-       (Maka),  Malayalam  (Mlym),  Mandaic (Mand), Manichaean (Mani), Marchen
-       (Marc), Masaram_Gondi (Gonm), Medefaidrin (Medf), Meetei_Mayek  (Mtei),
-       Mende_Kikakui  (Mend),  Meroitic_Cursive  (Merc),  Meroitic_Hieroglyphs
-       (Mero), Miao (Miao), Modi (Modi), Mongolian (Mong), Mro (Mroo), Multani
-       (Mult),   Myanmar   (Mymr),   Nabataean   (Nbar),  Nandinagari  (Nand),
-       New_Tai_Lue (Talu), Newa  (Newa),  Nko  (Nkoo),  Nushu  (Nshu),  Nyiak-
-       eng_Puachue_Hmong  (Hmnp), Ogham (Ogam), Ol_Chiki (Olck), Old_Hungarian
-       (Hung), Old_Italic (Olck), Old_North_Arabian (Narb), Old_Permic (Perm),
-       Old_Persian   (Orkh),  Old_Sogdian  (Sogo),  Old_South_Arabian  (Sarb),
-       Old_Turkic (Orkh), Old_Uyghur (Ougr), Oriya (Orya), Osage  (Osge),  Os-
-       manya   (Osma),  Pahawh_Hmong  (Hmng),  Palmyrene  (Palm),  Pau_Cin_Hau
-       (Pauc), Phags_Pa (Phag), Phoenician (Phnx), Psalter_Pahlavi (Phli), Re-
-       jang (Rjng), Runic (Runr), Samaritan (Samr), Saurashtra (Saur), Sharada
-       (Shrd), Shavian (Shaw), Siddham  (Sidd),  SignWriting  (Sgnw),  Sinhala
-       (Sinh),  Sogdian (Sogd), Sora_Sompeng (Sora), Soyombo (Soyo), Sundanese
-       (Sund), Syloti_Nagri (Sylo), Syriac (Syrc),  Tagalog  (Tglg),  Tagbanwa
-       (Tagb),  Tai_Le (Tale), Tai_Tham (Lana), Tai_Viet (Tavt), Takri (Takr),
-       Tamil (Taml), Tangsa  (Tngs),  Tangut  (Tang),  Telugu  (Telu),  Thaana
-       (Thaa),  Thai  (Thai), Tibetan (Tibt), Tifinagh (Tfng), Tirhuta (Tirh),
-       Toto (Toto), Ugaritic  (Ugar),  Vai  (Vaii),  Vithkuqi  (Vith),  Wancho
-       (Wcho),  Warang_Citi (Wara), Yezidi (Yezi), Yi (Yiii), Zanabazar_Square
-       (Zanb).
+         pcre2test -LS
 
 
-BIDI_PROPERTIES FOR \p AND \P
+THE BIDI_CLASS PROPERTY FOR \p AND \P
 
-         \p{Bidi_Control}         matches a Bidi control character
-         \p{Bidi_C}               matches a Bidi control character
          \p{Bidi_Class:}   matches a character with the given class
          \p{BC:}           matches a character with the given class
 
@@ -10846,8 +10784,8 @@ CHARACTER CLASSES
          word        same as \w
          xdigit      hexadecimal digit
 
-       In PCRE2, POSIX character set names recognize only ASCII characters  by
-       default,  but  some of them use Unicode properties if PCRE2_UCP is set.
+       In  PCRE2, POSIX character set names recognize only ASCII characters by
+       default, but some of them use Unicode properties if PCRE2_UCP  is  set.
        You can use \Q...\E inside a character class.
 
 
@@ -10892,8 +10830,8 @@ REPORTED MATCH POINT SETTING
 
          \K          set reported start of match
 
-       From release 10.38 \K is not permitted by default in lookaround  asser-
-       tions,  for  compatibility  with  Perl. However, if the PCRE2_EXTRA_AL-
+       From  release 10.38 \K is not permitted by default in lookaround asser-
+       tions, for compatibility with Perl.  However,  if  the  PCRE2_EXTRA_AL-
        LOW_LOOKAROUND_BSK option is set, the previous behaviour is re-enabled.
        When this option is set, \K is honoured in positive assertions, but ig-
        nored in negative ones.
@@ -10914,8 +10852,8 @@ CAPTURING
          (?|...)         non-capture group; reset group numbers for
                           capture groups in each alternative
 
-       In non-UTF modes, names may contain underscores and ASCII  letters  and
-       digits;  in  UTF  modes, any Unicode letters and Unicode decimal digits
+       In  non-UTF  modes, names may contain underscores and ASCII letters and
+       digits; in UTF modes, any Unicode letters and  Unicode  decimal  digits
        are permitted. In both cases, a name must not start with a digit.
 
 
@@ -10931,7 +10869,7 @@ COMMENT
 
 
 OPTION SETTING
-       Changes of these options within a group are automatically cancelled  at
+       Changes  of these options within a group are automatically cancelled at
        the end of the group.
 
          (?i)            caseless
@@ -10945,7 +10883,7 @@ OPTION SETTING
          (?-...)         unset option(s)
          (?^)            unset imnsx options
 
-       Unsetting  x or xx unsets both. Several options may be set at once, and
+       Unsetting x or xx unsets both. Several options may be set at once,  and
        a mixture of setting and unsetting such as (?i-x) is allowed, but there
        may be only one hyphen. Setting (but no unsetting) is allowed after (?^
        for example (?^in). An option setting may appear at the start of a non-
@@ -10967,11 +10905,11 @@ OPTION SETTING
          (*UTF)          set appropriate UTF mode for the library in use
          (*UCP)          set PCRE2_UCP (use Unicode properties for \d etc)
 
-       Note  that LIMIT_DEPTH, LIMIT_HEAP, and LIMIT_MATCH can only reduce the
-       value  of  the  limits  set  by  the   caller   of   pcre2_match()   or
-       pcre2_dfa_match(),  not  increase  them. LIMIT_RECURSION is an obsolete
+       Note that LIMIT_DEPTH, LIMIT_HEAP, and LIMIT_MATCH can only reduce  the
+       value   of   the   limits   set  by  the  caller  of  pcre2_match()  or
+       pcre2_dfa_match(), not increase them. LIMIT_RECURSION  is  an  obsolete
        synonym for LIMIT_DEPTH. The application can lock out the use of (*UTF)
-       and  (*UCP)  by setting the PCRE2_NEVER_UTF or PCRE2_NEVER_UCP options,
+       and (*UCP) by setting the PCRE2_NEVER_UTF or  PCRE2_NEVER_UCP  options,
        respectively, at compile time.
 
 
@@ -11092,16 +11030,16 @@ CONDITIONAL PATTERNS
          (?(VERSION[>]=n.m)  test PCRE2 version
          (?(assert)          assertion condition
 
-       Note the ambiguity of (?(R) and (?(Rn) which might be  named  reference
-       conditions  or  recursion  tests.  Such a condition is interpreted as a
+       Note  the  ambiguity of (?(R) and (?(Rn) which might be named reference
+       conditions or recursion tests. Such a condition  is  interpreted  as  a
        reference condition if the relevant named group exists.
 
 
 BACKTRACKING CONTROL
 
-       All backtracking control verbs may be in  the  form  (*VERB:NAME).  For
-       (*MARK)  the  name is mandatory, for the others it is optional. (*SKIP)
-       changes its behaviour if :NAME is present. The others just set  a  name
+       All  backtracking  control  verbs  may be in the form (*VERB:NAME). For
+       (*MARK) the name is mandatory, for the others it is  optional.  (*SKIP)
+       changes  its  behaviour if :NAME is present. The others just set a name
        for passing back to the caller, but this is not a name that (*SKIP) can
        see. The following act immediately they are reached:
 
@@ -11109,7 +11047,7 @@ BACKTRACKING CONTROL
          (*FAIL)         force backtrack; synonym (*F)
          (*MARK:NAME)    set name to be passed back; synonym (*:NAME)
 
-       The following act only when a subsequent match failure causes  a  back-
+       The  following  act only when a subsequent match failure causes a back-
        track to reach them. They all force a match failure, but they differ in
        what happens afterwards. Those that advance the start-of-match point do
        so only if the pattern is not anchored.
@@ -11121,7 +11059,7 @@ BACKTRACKING CONTROL
                          (*MARK:NAME); if not found, the (*SKIP) is ignored
          (*THEN)         local failure, backtrack to next alternation
 
-       The  effect  of one of these verbs in a group called as a subroutine is
+       The effect of one of these verbs in a group called as a  subroutine  is
        confined to the subroutine call.
 
 
@@ -11132,14 +11070,14 @@ CALLOUTS
          (?C"text")      callout with string data
 
        The allowed string delimiters are ` ' " ^ % # $ (which are the same for
-       the  start  and the end), and the starting delimiter { matched with the
-       ending delimiter }. To encode the ending delimiter within  the  string,
+       the start and the end), and the starting delimiter { matched  with  the
+       ending  delimiter  }. To encode the ending delimiter within the string,
        double it.
 
 
 SEE ALSO
 
-       pcre2pattern(3),    pcre2api(3),   pcre2callout(3),   pcre2matching(3),
+       pcre2pattern(3),   pcre2api(3),   pcre2callout(3),    pcre2matching(3),
        pcre2(3).
 
 
@@ -11152,8 +11090,8 @@ AUTHOR
 
 REVISION
 
-       Last updated: 28 December 2021
-       Copyright (c) 1997-2021 University of Cambridge.
+       Last updated: 12 January 2022
+       Copyright (c) 1997-2022 University of Cambridge.
 ------------------------------------------------------------------------------
  
  
diff --git a/doc/pcre2pattern.3 b/doc/pcre2pattern.3
index 7e2093d..dee4173 100644
--- a/doc/pcre2pattern.3
+++ b/doc/pcre2pattern.3
@@ -1,4 +1,4 @@
-.TH PCRE2PATTERN 3 "28 December 2021" "PCRE2 10.40"
+.TH PCRE2PATTERN 3 "12 January 2022" "PCRE2 10.40"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "PCRE2 REGULAR EXPRESSION DETAILS"
@@ -772,8 +772,15 @@ can be used in any mode, though in 8-bit and 16-bit non-UTF modes these
 sequences are of course limited to testing characters whose code points are
 less than U+0100 and U+10000, respectively. In 32-bit non-UTF mode, code points
 greater than 0x10ffff (the Unicode limit) may be encountered. These are all
-treated as being in the Unknown script and with an unassigned type. The extra
-escape sequences are:
+treated as being in the Unknown script and with an unassigned type. 
+.P
+Matching characters by Unicode property is not fast, because PCRE2 has to do a
+multistage table lookup in order to find a character's property. That is why
+the traditional escape sequences such as \ed and \ew do not use Unicode
+properties in PCRE2 by default, though you can make them do so by setting the
+PCRE2_UCP option or by starting the pattern with (*UCP).
+.P
+The extra escape sequences that provide property support are:
 .sp
   \ep{\fIxx\fP}   a character with the \fIxx\fP property
   \eP{\fIxx\fP}   a character without the \fIxx\fP property
@@ -783,19 +790,24 @@ The property names represented by \fIxx\fP above are not case-sensitive, and in
 accordance with Unicode's "loose matching" rules, spaces, hyphens, and
 underscores are ignored. There is support for Unicode script names, Unicode
 general category properties, "Any", which matches any character (including
-newline), Bidi_Control, Bidi_Class, and some special PCRE2 properties
-(described
+newline), Bidi_Class, a number of binary (yes/no) properties, and some special
+PCRE2 properties (described
 .\" HTML 
 .\" 
 below).
 .\"
-Other Perl properties such as "InMusicalSymbols" are not supported by PCRE2.
-Note that \eP{Any} does not match any characters, so always causes a match
-failure.
-.P
+Certain other Perl properties such as "InMusicalSymbols" are not supported by
+PCRE2. Note that \eP{Any} does not match any characters, so always causes a
+match failure.
+.
+.
+.
+.SS "Script properties for \ep and \eP"
+.rs
+.sp
 There are three different syntax forms for matching a script. Each Unicode
 character has a basic script and, optionally, a list of other scripts ("Script
-Extentions") with which it is commonly used. Using the Adlam script as an
+Extensions") with which it is commonly used. Using the Adlam script as an
 example, \ep{sc:Adlam} matches characters whose basic script is Adlam, whereas
 \ep{scx:Adlam} matches, in addition, characters that have Adlam in their
 extensions list. The full names "script" and "script extensions" for the
@@ -806,171 +818,18 @@ interpretation at release 5.26 and PCRE2 changed at release 10.40.
 .P
 Unassigned characters (and in non-UTF 32-bit mode, characters with code points
 greater than 0x10FFFF) are assigned the "Unknown" script. Others that are not
-part of an identified script are lumped together as "Common". The current list
-of script names and their 4-letter abbreviations is:
-.P
-Adlam (Adlm),
-Ahom (Ahom),
-Anatolian_Hieroglyphs (Hluw),
-Arabic (Arab),
-Armenian (Armn),
-Avestan (Avst),
-Balinese (Bali),
-Bamum (Bamu),
-Bassa_Vah (Bass),
-Batak (Batk),
-Bengali (Beng),
-Bhaiksuki (Bhks),
-Bopomofo (Bopo),
-Brahmi (Brah),
-Braille (Brai),
-Buginese (Bugi),
-Buhid (Buhd),
-Canadian_Aboriginal (Cans),
-Carian (Cari),
-Caucasian_Albanian (Aghb),
-Chakma (Cakm),
-Cham (Cham),
-Cherokee (Cher),
-Chorasmian (Chrs),
-Common (Zyyy),
-Coptic (Copt),
-Cuneiform (Xsux),
-Cypriot (Cprt),
-Cypro_Minoan (Cpmn),
-Cyrillic (Cyrl),
-Deseret (Dsrt),
-Devanagari (Deva),
-Dives_Akuru (Diak),
-Dogra (Dogr),
-Duployan (Dupl),
-Egyptian_Hieroglyphs (Egyp),
-Elbasan (Elba),
-Elymaic (Elym),
-Ethiopic (Ethi),
-Georgian (Geor),
-Glagolitic (Glag),
-Gothic (Goth),
-Grantha (Gran),
-Greek (Grek),
-Gujarati (Gujr),
-Gunjala_Gondi (Gong),
-Gurmukhi (Guru),
-Han (Hani),
-Hangul (Hang),
-Hanifi_Rohingya (Rohg),
-Hanunoo (Hano),
-Hatran (Hatr),
-Hebrew (Hebr),
-Hiragana (Hira),
-Imperial_Aramaic (Armi),
-Inherited (Zinh),
-Inscriptional_Pahlavi (Phli),
-Inscriptional_Parthian (Prti),
-Javanese (Java),
-Kaithi (Kthi),
-Kannada (Knda),
-Katakana (Kana),
-Kayah_Li (Kali),
-Kharoshthi (Khar),
-Khitan_Small_Script (Kits),
-Khmer (Khmr),
-Khojki (Khoj),
-Khudawadi (Sind),
-Lao (Laoo),
-Latin (Latn),
-Lepcha (Lepc),
-Limbu (Limb),
-Linear_A (Lina),
-Linear_B (Linb),
-Lisu (Lisu),
-Lycian (Lyci),
-Lydian (Lydi),
-Mahajani (Majh),
-Makasar (Maka),
-Malayalam (Mlym),
-Mandaic (Mand),
-Manichaean (Mani),
-Marchen (Marc),
-Masaram_Gondi (Gonm),
-Medefaidrin (Medf),
-Meetei_Mayek (Mtei),
-Mende_Kikakui (Mend),
-Meroitic_Cursive (Merc),
-Meroitic_Hieroglyphs (Mero),
-Miao (Miao),
-Modi (Modi),
-Mongolian (Mong),
-Mro (Mroo),
-Multani (Mult),
-Myanmar (Mymr),
-Nabataean (Nbar),
-Nandinagari (Nand),
-New_Tai_Lue (Talu),
-Newa (Newa),
-Nko (Nkoo),
-Nushu (Nshu),
-Nyiakeng_Puachue_Hmong (Hmnp),
-Ogham (Ogam),
-Ol_Chiki (Olck),
-Old_Hungarian (Hung),
-Old_Italic (Olck),
-Old_North_Arabian (Narb),
-Old_Permic (Perm),
-Old_Persian (Orkh),
-Old_Sogdian (Sogo),
-Old_South_Arabian (Sarb),
-Old_Turkic (Orkh),
-Old_Uyghur (Ougr),
-Oriya (Orya),
-Osage (Osge),
-Osmanya (Osma),
-Pahawh_Hmong (Hmng),
-Palmyrene (Palm),
-Pau_Cin_Hau (Pauc),
-Phags_Pa (Phag),
-Phoenician (Phnx),
-Psalter_Pahlavi (Phli),
-Rejang (Rjng),
-Runic (Runr),
-Samaritan (Samr),
-Saurashtra (Saur),
-Sharada (Shrd),
-Shavian (Shaw),
-Siddham (Sidd),
-SignWriting (Sgnw),
-Sinhala (Sinh),
-Sogdian (Sogd),
-Sora_Sompeng (Sora),
-Soyombo (Soyo),
-Sundanese (Sund),
-Syloti_Nagri (Sylo),
-Syriac (Syrc),
-Tagalog (Tglg),
-Tagbanwa (Tagb),
-Tai_Le (Tale),
-Tai_Tham (Lana),
-Tai_Viet (Tavt),
-Takri (Takr),
-Tamil (Taml),
-Tangsa (Tngs),
-Tangut (Tang),
-Telugu (Telu),
-Thaana (Thaa),
-Thai (Thai),
-Tibetan (Tibt),
-Tifinagh (Tfng),
-Tirhuta (Tirh),
-Toto (Toto),
-Ugaritic (Ugar),
-Vai (Vaii),
-Vithkuqi (Vith),
-Wancho (Wcho),
-Warang_Citi (Wara),
-Yezidi (Yezi),
-Yi (Yiii),
-Zanabazar_Square (Zanb).
-.P
+part of an identified script are lumped together as "Common". The current list 
+of recognized script names and their 4-character abbreviations can be obtained 
+by running this command:
+.sp
+  pcre2test -LS
+.sp   
+.
+.
+.
+.SS "The general category property for \ep and \eP"
+.rs
+.sp
 Each character has exactly one Unicode general category property, specified by
 a two-letter abbreviation. For compatibility with Perl, negation can be
 specified by including a circumflex between the opening brace and the property
@@ -1056,22 +915,22 @@ Unicode table.
 Specifying caseless matching does not affect these escape sequences. For
 example, \ep{Lu} always matches only upper case letters. This is different from
 the behaviour of current versions of Perl.
-.P
-Matching characters by Unicode property is not fast, because PCRE2 has to do a
-multistage table lookup in order to find a character's property. That is why
-the traditional escape sequences such as \ed and \ew do not use Unicode
-properties in PCRE2 by default, though you can make them do so by setting the
-PCRE2_UCP option or by starting the pattern with (*UCP).
 .
 .
-.SS "Bi-directional properties for \ep and \eP"
+.SS "Binary (yes/no) properties for \ep and \eP"
 .rs
 .sp
-Two properties relating to bi-directional text (each with a shorter synonym)
-are supported:
+Unicode defines a number of binary properties, that is, properties whose only
+values are true or false. You can obtain a list of those that are recognized by
+\ep and \eP, along with their abbreviations, by running this command:
+.sp
+  pcre2test -LP
+.sp
+.
+.
+.SS "The Bidi_Class property for \ep and \eP"
+.rs
 .sp
-  \ep{Bidi_Control}         matches a Bidi control character
-  \ep{Bidi_C}               matches a Bidi control character
   \ep{Bidi_Class:}   matches a character with the given class
   \ep{BC:}           matches a character with the given class
 .sp
@@ -1101,8 +960,8 @@ The recognized classes are:
   S           segment separator
   WS          which space
 .sp
-For Bidi_Class, an equals sign may be used instead of a colon. The class names
-are case-insensitive; only the short names listed above are recognized.
+An equals sign may be used instead of a colon. The class names are
+case-insensitive; only the short names listed above are recognized.
 .
 .
 .SS Extended grapheme clusters
@@ -3955,6 +3814,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 28 December 2021
-Copyright (c) 1997-2021 University of Cambridge.
+Last updated: 12 January 2022
+Copyright (c) 1997-2022 University of Cambridge.
 .fi
diff --git a/doc/pcre2syntax.3 b/doc/pcre2syntax.3
index c816c4e..d05d23b 100644
--- a/doc/pcre2syntax.3
+++ b/doc/pcre2syntax.3
@@ -1,4 +1,4 @@
-.TH PCRE2SYNTAX 3 "28 December 2021" "PCRE2 10.40"
+.TH PCRE2SYNTAX 3 "12 January 2022" "PCRE2 10.40"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "PCRE2 REGULAR EXPRESSION SYNTAX SUMMARY"
@@ -172,181 +172,31 @@ Perl and POSIX space are now the same. Perl added VT to its space character set
 at release 5.18.
 .
 .
+.SH "BINARY PROPERTIES FOR \ep AND \eP"
+.rs
+.sp
+Unicode defines a number of binary properties, that is, properties whose only
+values are true or false. You can obtain a list of those that are recognized by
+\ep and \eP, along with their abbreviations, by running this command:
+.sp
+  pcre2test -LP
+.
+.
+.
 .SH "SCRIPT MATCHING WITH \ep AND \eP"
 .rs
 .sp
-The following script names and their 4-letter abbreviations are recognized in
+Many script names and their 4-letter abbreviations are recognized in
 \ep{sc:...} or \ep{scx:...} items, or on their own with \ep (and also \eP of
-course):
-.P
-Adlam (Adlm),
-Ahom (Ahom),
-Anatolian_Hieroglyphs (Hluw),
-Arabic (Arab),
-Armenian (Armn),
-Avestan (Avst),
-Balinese (Bali),
-Bamum (Bamu),
-Bassa_Vah (Bass),
-Batak (Batk),
-Bengali (Beng),
-Bhaiksuki (Bhks),
-Bopomofo (Bopo),
-Brahmi (Brah),
-Braille (Brai),
-Buginese (Bugi),
-Buhid (Buhd),
-Canadian_Aboriginal (Cans),
-Carian (Cari),
-Caucasian_Albanian (Aghb),
-Chakma (Cakm),
-Cham (Cham),
-Cherokee (Cher),
-Chorasmian (Chrs),
-Common (Zyyy),
-Coptic (Copt),
-Cuneiform (Xsux),
-Cypriot (Cprt),
-Cypro_Minoan (Cpmn),
-Cyrillic (Cyrl),
-Deseret (Dsrt),
-Devanagari (Deva),
-Dives_Akuru (Diak),
-Dogra (Dogr),
-Duployan (Dupl),
-Egyptian_Hieroglyphs (Egyp),
-Elbasan (Elba),
-Elymaic (Elym),
-Ethiopic (Ethi),
-Georgian (Geor),
-Glagolitic (Glag),
-Gothic (Goth),
-Grantha (Gran),
-Greek (Grek),
-Gujarati (Gujr),
-Gunjala_Gondi (Gong),
-Gurmukhi (Guru),
-Han (Hani),
-Hangul (Hang),
-Hanifi_Rohingya (Rohg),
-Hanunoo (Hano),
-Hatran (Hatr),
-Hebrew (Hebr),
-Hiragana (Hira),
-Imperial_Aramaic (Armi),
-Inherited (Zinh),
-Inscriptional_Pahlavi (Phli),
-Inscriptional_Parthian (Prti),
-Javanese (Java),
-Kaithi (Kthi),
-Kannada (Knda),
-Katakana (Kana),
-Kayah_Li (Kali),
-Kharoshthi (Khar),
-Khitan_Small_Script (Kits),
-Khmer (Khmr),
-Khojki (Khoj),
-Khudawadi (Sind),
-Lao (Laoo),
-Latin (Latn),
-Lepcha (Lepc),
-Limbu (Limb),
-Linear_A (Lina),
-Linear_B (Linb),
-Lisu (Lisu),
-Lycian (Lyci),
-Lydian (Lydi),
-Mahajani (Majh),
-Makasar (Maka),
-Malayalam (Mlym),
-Mandaic (Mand),
-Manichaean (Mani),
-Marchen (Marc),
-Masaram_Gondi (Gonm),
-Medefaidrin (Medf),
-Meetei_Mayek (Mtei),
-Mende_Kikakui (Mend),
-Meroitic_Cursive (Merc),
-Meroitic_Hieroglyphs (Mero),
-Miao (Miao),
-Modi (Modi),
-Mongolian (Mong),
-Mro (Mroo),
-Multani (Mult),
-Myanmar (Mymr),
-Nabataean (Nbar),
-Nandinagari (Nand),
-New_Tai_Lue (Talu),
-Newa (Newa),
-Nko (Nkoo),
-Nushu (Nshu),
-Nyiakeng_Puachue_Hmong (Hmnp),
-Ogham (Ogam),
-Ol_Chiki (Olck),
-Old_Hungarian (Hung),
-Old_Italic (Olck),
-Old_North_Arabian (Narb),
-Old_Permic (Perm),
-Old_Persian (Orkh),
-Old_Sogdian (Sogo),
-Old_South_Arabian (Sarb),
-Old_Turkic (Orkh),
-Old_Uyghur (Ougr),
-Oriya (Orya),
-Osage (Osge),
-Osmanya (Osma),
-Pahawh_Hmong (Hmng),
-Palmyrene (Palm),
-Pau_Cin_Hau (Pauc),
-Phags_Pa (Phag),
-Phoenician (Phnx),
-Psalter_Pahlavi (Phli),
-Rejang (Rjng),
-Runic (Runr),
-Samaritan (Samr),
-Saurashtra (Saur),
-Sharada (Shrd),
-Shavian (Shaw),
-Siddham (Sidd),
-SignWriting (Sgnw),
-Sinhala (Sinh),
-Sogdian (Sogd),
-Sora_Sompeng (Sora),
-Soyombo (Soyo),
-Sundanese (Sund),
-Syloti_Nagri (Sylo),
-Syriac (Syrc),
-Tagalog (Tglg),
-Tagbanwa (Tagb),
-Tai_Le (Tale),
-Tai_Tham (Lana),
-Tai_Viet (Tavt),
-Takri (Takr),
-Tamil (Taml),
-Tangsa (Tngs),
-Tangut (Tang),
-Telugu (Telu),
-Thaana (Thaa),
-Thai (Thai),
-Tibetan (Tibt),
-Tifinagh (Tfng),
-Tirhuta (Tirh),
-Toto (Toto),
-Ugaritic (Ugar),
-Vai (Vaii),
-Vithkuqi (Vith),
-Wancho (Wcho),
-Warang_Citi (Wara),
-Yezidi (Yezi),
-Yi (Yiii),
-Zanabazar_Square (Zanb).
+course). You can obtain a list of these scripts by running this command:
+.sp
+  pcre2test -LS
 .
 .
-.SH "BIDI_PROPERTIES FOR \ep AND \eP"
+.
+.SH "THE BIDI_CLASS PROPERTY FOR \ep AND \eP"
 .rs
 .sp
-  \ep{Bidi_Control}         matches a Bidi control character
-  \ep{Bidi_C}               matches a Bidi control character
   \ep{Bidi_Class:}   matches a character with the given class
   \ep{BC:}           matches a character with the given class
 .sp
@@ -728,6 +578,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 28 December 2021
-Copyright (c) 1997-2021 University of Cambridge.
+Last updated: 12 January 2022
+Copyright (c) 1997-2022 University of Cambridge.
 .fi
diff --git a/doc/pcre2test.txt b/doc/pcre2test.txt
index 06456a1..ed7dd20 100644
--- a/doc/pcre2test.txt
+++ b/doc/pcre2test.txt
@@ -197,7 +197,17 @@ COMMAND LINE OPTIONS
 
        -LM       List modifiers: write a list of available pattern and subject
                  modifiers to the standard output, then exit  with  zero  exit
-                 code.  All other options are ignored.  If both -C and -LM are
+                 code.  All other options are ignored.  If both -C and any -Lx
+                 options are present, whichever is first is recognized.
+
+       -LP       List properties: write a list of recognized  Unicode  proper-
+                 ties  to  the standard output, then exit with zero exit code.
+                 All other options are ignored. If both -C and any -Lx options
+                 are present, whichever is first is recognized.
+
+       -LS       List  scripts: write a list of recogized Unicode script names
+                 to the standard output, then exit with zero  exit  code.  All
+                 other options are ignored. If both -C and any -Lx options are
                  present, whichever is first is recognized.
 
        -pattern modifier-list
@@ -1939,5 +1949,5 @@ AUTHOR
 
 REVISION
 
-       Last updated: 28 November 2021
-       Copyright (c) 1997-2021 University of Cambridge.
+       Last updated: 12 January 2022
+       Copyright (c) 1997-2022 University of Cambridge.