Increase name length to 128

ChangeLog

@@ -27,6 +27,9 @@ example pattern is: /(((?<=123?456456|ABC)))(?<=\2)/
    (d) Made the output in standalone mode more readable.
 
    (e) General code tidies.
+   
+3. Increase the maximum length of a name for a group from 32 to 128 because 
+there is a user for whom 32 is too small. 
 
 
 Version 10.43 16-February-2024

configure.ac

@@ -9,9 +9,9 @@ dnl The PCRE2_PRERELEASE feature is for identifying release candidates. It might
 dnl be defined as -RC2, for example. For real releases, it should be empty.
 
 m4_define(pcre2_major, [10])
-m4_define(pcre2_minor, [43])
-m4_define(pcre2_prerelease, [])
-m4_define(pcre2_date, [2024-02-16])
+m4_define(pcre2_minor, [44])
+m4_define(pcre2_prerelease, [-DEV])
+m4_define(pcre2_date, [2024-03-11])
 
 # Libtool shared library interface versions (current:revision:age)
 m4_define(libpcre2_8_version,     [12:0:12])
@@ -883,7 +883,7 @@ AC_DEFINE_UNQUOTED([HEAP_LIMIT], [$with_heap_limit], [
   a pattern. It applies to both pcre2_match() and pcre2_dfa_match(). It does
   not apply to JIT matching. The value is in kibibytes (units of 1024 bytes).])
 
-AC_DEFINE([MAX_NAME_SIZE], [32], [
+AC_DEFINE([MAX_NAME_SIZE], [128], [
   This limit is parameterized just in case anybody ever wants to
   change it. Care must be taken if it is increased, because it guards
   against integer overflow caused by enormously large patterns.])

doc/html/pcre2pattern.html

@@ -1843,7 +1843,7 @@ using the Python syntax. PCRE2 supports both the Perl and the Python syntax.
 </P>
 <P>
 In PCRE2, a capture group can be named in one of three ways: (?&#60;name&#62;...) or
-(?'name'...) as in Perl, or (?P&#60;name&#62;...) as in Python. Names may be up to 32
+(?'name'...) as in Perl, or (?P&#60;name&#62;...) as in Python. Names may be up to 128
 code units long. When PCRE2_UTF is not set, they may contain only ASCII
 alphanumeric characters and underscores, but must start with a non-digit. When
 PCRE2_UTF is set, the syntax of group names is extended to allow any Unicode
@@ -3844,7 +3844,7 @@ Cambridge, England.
 </P>
 <br><a name="SEC32" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 19 January 2024
+Last updated: 11 March 2024
 <br>
 Copyright &copy; 1997-2024 University of Cambridge.
 <br>

doc/pcre2demo.3

@@ -1,4 +1,4 @@
-.TH PCRE2DEMO 3 "21 February 2024" "PCRE2 10.43"
+.TH PCRE2DEMO 3 "11 March 2024" "PCRE2 10.43"
 .\"AUTOMATICALLY GENERATED BY PrepareRelease - do not EDIT!
 .SH NAME
 PCRE2DEMO - A demonstration C program for PCRE2

doc/pcre2pattern.3

@@ -1,4 +1,4 @@
-.TH PCRE2PATTERN 3 "19 January 2024" "PCRE2 10.43"
+.TH PCRE2PATTERN 3 "11 March 2024" "PCRE2 10.44"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "PCRE2 REGULAR EXPRESSION DETAILS"
@@ -1844,7 +1844,7 @@ the naming of capture groups. This feature was not added to Perl until release
 using the Python syntax. PCRE2 supports both the Perl and the Python syntax.
 .P
 In PCRE2, a capture group can be named in one of three ways: (?<name>...) or
-(?'name'...) as in Perl, or (?P<name>...) as in Python. Names may be up to 32
+(?'name'...) as in Perl, or (?P<name>...) as in Python. Names may be up to 128
 code units long. When PCRE2_UTF is not set, they may contain only ASCII
 alphanumeric characters and underscores, but must start with a non-digit. When
 PCRE2_UTF is set, the syntax of group names is extended to allow any Unicode
@@ -3889,6 +3889,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 19 January 2024
+Last updated: 11 March 2024
 Copyright (c) 1997-2024 University of Cambridge.
 .fi

testdata/testinput10

@@ -487,11 +487,11 @@
     
 # Check name length with non-ASCII characters 
 
-/(?'ABáC678901234567890123456789012'...)/utf
+/(?'ABáC678901234567890123456789012012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf
 
-/(?'ABáC6789012345678901234567890123'...)/utf
+/(?'ABáC6789012345678901234567890123012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf
 
-/(?'ABZC6789012345678901234567890123'...)/utf
+/(?'ABZC6789012345678901234567890123012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf
 
 /(?(n/utf
 

testdata/testinput2

@@ -4680,9 +4680,9 @@ B)x/alt_verbnames,mark
 /(?<=\K.)/g,replace=-,allow_lookaround_bsk
     ab
 
-/(?'abcdefghijklmnopqrstuvwxyzABCDEFG'toolong)/
+/(?'abcdefghijklmnopqrstuvwxyzABCDEFGabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEFGH'toolong)/
 
-/(?'abcdefghijklmnopqrstuvwxyzABCDEF'justright)/
+/(?'abcdefghijklmnopqrstuvwxyzABCDEFGabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEFG'justright)/
 
 # These two use zero-termination
 /abcd/max_pattern_length=3
@@ -4949,7 +4949,7 @@ a)"xI
 /{<7B>̈́<EFBFBD>̈́<EFBFBD>{'{22{2{{2{'{22{{22{2{'{22{2{{2{{222{{2{'{22{2{22{2{'{22{2{{2{'{22{2{22{2{'{'{22{2{22{2{'{22{2{{2{'{22{2{22{2{'{222{2Ą̈́<C484>̈́<EFBFBD>{'{22{2{{2{'{22{{11{2{'{22{2{{2{{'{22{2{{2{'{22{{22{1{'{22{2{{2{{222{{2{'{22{2{22{2{'{/auto_callout
 
 //
-\=get=i00000000000000000000000000000000
+\=get=i00000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
 \=get=i2345678901234567890123456789012,get=i1245678901234567890123456789012
 
 "(?(?C))"

testdata/testoutput10

@@ -1615,12 +1615,12 @@ No match
     
 # Check name length with non-ASCII characters 
 
-/(?'ABáC678901234567890123456789012'...)/utf
+/(?'ABáC678901234567890123456789012012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf
 
-/(?'ABáC6789012345678901234567890123'...)/utf
-Failed: error 148 at offset 36: subpattern name is too long (maximum 32 code units)
+/(?'ABáC6789012345678901234567890123012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf
+Failed: error 148 at offset 132: subpattern name is too long (maximum 128 code units)
 
-/(?'ABZC6789012345678901234567890123'...)/utf
+/(?'ABZC6789012345678901234567890123012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf
 
 /(?(n/utf
 Failed: error 142 at offset 4: syntax error in subpattern name (missing terminator?)

testdata/testoutput2

@@ -14935,10 +14935,10 @@ Failed: error -60: match with end before start or start moved backwards is not s
     ab
 Failed: error -60: match with end before start or start moved backwards is not supported
 
-/(?'abcdefghijklmnopqrstuvwxyzABCDEFG'toolong)/
-Failed: error 148 at offset 36: subpattern name is too long (maximum 32 code units)
+/(?'abcdefghijklmnopqrstuvwxyzABCDEFGabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEFGH'toolong)/
+Failed: error 148 at offset 132: subpattern name is too long (maximum 128 code units)
 
-/(?'abcdefghijklmnopqrstuvwxyzABCDEF'justright)/
+/(?'abcdefghijklmnopqrstuvwxyzABCDEFGabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEFG'justright)/
 
 # These two use zero-termination
 /abcd/max_pattern_length=3
@@ -15549,7 +15549,7 @@ Failed: error 157 at offset 6: \g is not followed by a braced, angle-bracketed,
 /{<7B>̈́<EFBFBD>̈́<EFBFBD>{'{22{2{{2{'{22{{22{2{'{22{2{{2{{222{{2{'{22{2{22{2{'{22{2{{2{'{22{2{22{2{'{'{22{2{22{2{'{22{2{{2{'{22{2{22{2{'{222{2Ą̈́<C484>̈́<EFBFBD>{'{22{2{{2{'{22{{11{2{'{22{2{{2{{'{22{2{{2{'{22{{22{1{'{22{2{{2{{222{{2{'{22{2{22{2{'{/auto_callout
 
 //
-\=get=i00000000000000000000000000000000
+\=get=i00000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
 ** Group name in 'get' is too long
 \=get=i2345678901234567890123456789012,get=i1245678901234567890123456789012
 ** Too many characters in named 'get' modifiers