From 7adca3f3973689d4123c6f2c6f825888cd95bbe7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Carlo=20Marcelo=20Arenas=20Bel=C3=B3n?= Date: Sun, 17 Aug 2025 20:45:17 -0700 Subject: [PATCH 1/2] maint: introduce LintMan to aid on tracking/updating values Allow tagging the documentation with a `#define` value that could be then updated programmatically. Update the value for MAX_NAME_SIZE in pcre2limits.3 that was missing since ced3b0f0 (Increase name length to 128, 2024-03-11) and while at it, improve on its description and add a tag for a related variable. For completeness, add also a tag to the same value in pcre2pattern.3 and the configuration for VMS that was missing since 6c670c78 (Update overlooked cmake update of name size to 128, 2024-03-11) and add it to UpdateAlways so it can be used in a developer tree. --- doc/html/pcre2limits.html | 9 ++++-- doc/html/pcre2pattern.html | 6 ++-- doc/pcre2.txt | 10 +++--- doc/pcre2limits.3 | 11 +++++-- doc/pcre2pattern.3 | 7 ++-- maint/CheckMan | 1 + maint/LintMan | 66 ++++++++++++++++++++++++++++++++++++++ maint/README | 4 +++ maint/UpdateAlways | 7 ++++ vms/configure.com | 2 +- 10 files changed, 106 insertions(+), 17 deletions(-) create mode 100755 maint/LintMan diff --git a/doc/html/pcre2limits.html b/doc/html/pcre2limits.html index eabc4e873..1afb44eca 100644 --- a/doc/html/pcre2limits.html +++ b/doc/html/pcre2limits.html @@ -64,8 +64,11 @@

a compile context.

-The maximum length of name for a named capture group is 32 code units, and the -maximum number of such groups is 10000. +The maximum length of the name for a named capture group as well as the number +of such groups is configurable at build time. The maximum length for the name +defaults to +128 code units, and the maximum number of such groups to +10000.

The maximum length of a name in a (*MARK), (*PRUNE), (*SKIP), or (*THEN) verb @@ -96,7 +99,7 @@

REVISION

-Last updated: 16 August 2023 +Last updated: 17 August 2025
Copyright © 1997-2023 University of Cambridge.
diff --git a/doc/html/pcre2pattern.html b/doc/html/pcre2pattern.html index 0bbd71adf..f301be267 100644 --- a/doc/html/pcre2pattern.html +++ b/doc/html/pcre2pattern.html @@ -2007,8 +2007,8 @@

NAMED CAPTURE GROUPS

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 128 -code units long. When PCRE2_UTF is not set, they may contain only ASCII +(?'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 letter or Unicode decimal digit. In other words, group names must match one of @@ -4183,7 +4183,7 @@

AUTHOR

REVISION

-Last updated: 28 March 2025 +Last updated: 17 August 2025
Copyright © 1997-2024 University of Cambridge.
diff --git a/doc/pcre2.txt b/doc/pcre2.txt index 40db85f00..247941c6e 100644 --- a/doc/pcre2.txt +++ b/doc/pcre2.txt @@ -6238,8 +6238,10 @@ SIZE AND OTHER LIMITATIONS is set to 250. An application can change this limit by calling pcre2_set_parens_nest_limit() to set the limit in a compile context. - The maximum length of name for a named capture group is 32 code units, - and the maximum number of such groups is 10000. + The maximum length of the name for a named capture group as well as the + number of such groups is configurable at build time. The maximum length + for the name defaults to 128 code units, and the maximum number of such + groups to 10000. The maximum length of a name in a (*MARK), (*PRUNE), (*SKIP), or (*THEN) verb is 255 code units for the 8-bit library and 65535 code @@ -6262,7 +6264,7 @@ AUTHOR REVISION - Last updated: 16 August 2023 + Last updated: 17 August 2025 Copyright (c) 1997-2023 University of Cambridge. @@ -10747,7 +10749,7 @@ AUTHOR REVISION - Last updated: 28 March 2025 + Last updated: 17 August 2025 Copyright (c) 1997-2024 University of Cambridge. diff --git a/doc/pcre2limits.3 b/doc/pcre2limits.3 index 423dedf60..5e51e5869 100644 --- a/doc/pcre2limits.3 +++ b/doc/pcre2limits.3 @@ -47,8 +47,13 @@ when PCRE2 is built; if not, the default is set to 250. An application can change this limit by calling pcre2_set_parens_nest_limit() to set the limit in a compile context. .P -The maximum length of name for a named capture group is 32 code units, and the -maximum number of such groups is 10000. +The maximum length of the name for a named capture group as well as the number +of such groups is configurable at build time. The maximum length for the name +defaults to +.\" DEFINE MAX_NAME_SIZE +128 code units, and the maximum number of such groups to +.\" DEFINE MAX_NAME_COUNT +10000. .P The maximum length of a name in a (*MARK), (*PRUNE), (*SKIP), or (*THEN) verb is 255 code units for the 8-bit library and 65535 code units for the 16-bit and @@ -76,6 +81,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 16 August 2023 +Last updated: 17 August 2025 Copyright (c) 1997-2023 University of Cambridge. .fi diff --git a/doc/pcre2pattern.3 b/doc/pcre2pattern.3 index e49b5a338..45b6f01c1 100644 --- a/doc/pcre2pattern.3 +++ b/doc/pcre2pattern.3 @@ -2015,8 +2015,9 @@ 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: (?...) or -(?'name'...) as in Perl, or (?P...) as in Python. Names may be up to 128 -code units long. When PCRE2_UTF is not set, they may contain only ASCII +(?'name'...) as in Perl, or (?P...) as in Python. Names may be up to +.\" DEFINE MAX_NAME_SIZE +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 letter or Unicode decimal digit. In other words, group names must match one of @@ -4229,6 +4230,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 28 March 2025 +Last updated: 17 August 2025 Copyright (c) 1997-2024 University of Cambridge. .fi diff --git a/maint/CheckMan b/maint/CheckMan index 75cae62f1..b34651e96 100755 --- a/maint/CheckMan +++ b/maint/CheckMan @@ -39,6 +39,7 @@ while (scalar(@ARGV) > 0) ^\.P\s*$| ^\.PP\s*$| ^\.\\"(?:\ HREF)?\s*$| + ^\.\\"\sDEFINE\s\w+$| ^\.\\"\sHTML\s\s*$| ^\.\\"\sHTML\s<\/a>\s*$| ^\.\\"\s<\/a>\s*$| diff --git a/maint/LintMan b/maint/LintMan new file mode 100755 index 000000000..b0bc5f88b --- /dev/null +++ b/maint/LintMan @@ -0,0 +1,66 @@ +#!/usr/bin/perl + +use warnings; +use strict; +use Getopt::Long; +use vars qw /$opt_verbose/; + +# A script to scan PCRE2's man pages to check for values that might need to +# be updatd to match the code. +# +# It updates numerical values after \" DEFINE or errors if name is +# not found. + +my $file; +my %defs; + +foreach $file ("../src/config.h") + { + open (INCLUDE, $file) or die "Failed to open include $file\n"; + + while () + { + next unless /^#define ([[:upper:]_\d]+)\s+(\d+)/a; + $defs{$1} = $2; + } + + close(INCLUDE); + } + +GetOptions("verbose"); +while (scalar(@ARGV) > 0) + { + $file = shift @ARGV; + + open my $fh, "+<", $file or die "Failed to open $file\n"; + + my @lines = <$fh>; + my $updated = 0; + + foreach my $index (0 .. $#lines) + { + if ($lines[$index] =~ /^\.\\"\sDEFINE\s([[:upper:]_\d]+)$/a) + { + my $l = $index + 1; + die "Invalid DEFINE line $l of $file\n" unless defined $lines[$l]; + + my $key = $1; + die "Bad DEFINE key $key line $l of $file\n" unless exists $defs{$key}; + + my $value = $defs{$key}; + if ($lines[$index + 1] !~ /^$value\b/) + { + $updated += $lines[$index + 1] =~ s/^\d+/$value/a; + print "Updated $key in $file to $value\n" if $opt_verbose; + } + } + } + + if ($updated > 0) + { + seek($fh, 0, 0); + print $fh @lines; + truncate($fh, tell($fh)); + } + close($fh); + } diff --git a/maint/README b/maint/README index 7db649844..9763d2346 100644 --- a/maint/README +++ b/maint/README @@ -60,6 +60,10 @@ GenerateUcpTables.py GenerateCommon.py and Unicode data files. The generated file contains tables for looking up Unicode property names. +LintMan + A Perl script to check and update magic numbers in the documentation that + correspond to configurable settings in the codebase. + manifest-* Data files used to verify the contents of the distribution tarball and `make install` file lists. diff --git a/maint/UpdateAlways b/maint/UpdateAlways index ca89fa05a..13cf27197 100755 --- a/maint/UpdateAlways +++ b/maint/UpdateAlways @@ -19,6 +19,8 @@ # Detrail A Perl script that removes trailing spaces from files. +# LintMan A Perl script that lints man pages looking for inconsistencies. + # doc/index.html.src # A file that is copied as index.html into the doc/html directory # when the HTML documentation is built. It works like this so that @@ -54,6 +56,11 @@ echo Processing documentation perl ../maint/CheckMan *.1 *.3 if [ $? != 0 ] ; then exit 1; fi +if [ -f ../src/config.h ] ; then + perl ../maint/LintMan -v *.3 + if [ $? != 0 ] ; then exit 1; fi +fi + # Verify the version number in the man pages for file in *.1 *.3 ; do diff --git a/vms/configure.com b/vms/configure.com index eccb61980..19c9ff5bb 100644 --- a/vms/configure.com +++ b/vms/configure.com @@ -905,7 +905,7 @@ sure both macros are undefined; an emulation function will then be used. */ #define PCRE2_EXPORT #define LINK_SIZE 2 #define MAX_NAME_COUNT 10000 -#define MAX_NAME_SIZE 32 +#define MAX_NAME_SIZE 128 #define MATCH_LIMIT 10000000 #define HEAP_LIMIT 20000000 #define NEWLINE_DEFAULT 2 From bac89d5b2ed7270ca044f773a76b074860d811cb Mon Sep 17 00:00:00 2001 From: Nicholas Wilson Date: Fri, 29 Aug 2025 09:57:39 +0000 Subject: [PATCH 2/2] Make documentation match config.h.generic --- maint/LintMan | 4 ++-- maint/UpdateAlways | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/maint/LintMan b/maint/LintMan index b0bc5f88b..924e9533d 100755 --- a/maint/LintMan +++ b/maint/LintMan @@ -6,7 +6,7 @@ use Getopt::Long; use vars qw /$opt_verbose/; # A script to scan PCRE2's man pages to check for values that might need to -# be updatd to match the code. +# be updated to match the code. # # It updates numerical values after \" DEFINE or errors if name is # not found. @@ -14,7 +14,7 @@ use vars qw /$opt_verbose/; my $file; my %defs; -foreach $file ("../src/config.h") +foreach $file ("../src/config.h.generic") { open (INCLUDE, $file) or die "Failed to open include $file\n"; diff --git a/maint/UpdateAlways b/maint/UpdateAlways index 13cf27197..6ae1c8d8b 100755 --- a/maint/UpdateAlways +++ b/maint/UpdateAlways @@ -56,7 +56,7 @@ echo Processing documentation perl ../maint/CheckMan *.1 *.3 if [ $? != 0 ] ; then exit 1; fi -if [ -f ../src/config.h ] ; then +if [ -f ../src/config.h.generic ] ; then perl ../maint/LintMan -v *.3 if [ $? != 0 ] ; then exit 1; fi fi