Documentation scripts
This commit is contained in:
Philip.Hazel
parent
a625f0ea01
commit
d5495a30f4
|
|
@ -0,0 +1,313 @@
|
|||
#! /usr/bin/perl -w
|
||||
|
||||
# Script to turn PCRE2 man pages into HTML
|
||||
|
||||
|
||||
# Subroutine to handle font changes and other escapes
|
||||
|
||||
sub do_line {
|
||||
my($s) = $_[0];
|
||||
|
||||
$s =~ s/</</g; # Deal with < and >
|
||||
$s =~ s/>/>/g;
|
||||
$s =~ s"\\fI(.*?)\\f[RP]"<i>$1</i>"g;
|
||||
$s =~ s"\\fB(.*?)\\f[RP]"<b>$1</b>"g;
|
||||
$s =~ s"\\e"\\"g;
|
||||
$s =~ s/(?<=Copyright )\(c\)/©/g;
|
||||
$s;
|
||||
}
|
||||
|
||||
# Subroutine to ensure not in a paragraph
|
||||
|
||||
sub end_para {
|
||||
if ($inpara)
|
||||
{
|
||||
print TEMP "</PRE>\n" if ($inpre);
|
||||
print TEMP "</P>\n";
|
||||
}
|
||||
$inpara = $inpre = 0;
|
||||
$wrotetext = 0;
|
||||
}
|
||||
|
||||
# Subroutine to start a new paragraph
|
||||
|
||||
sub new_para {
|
||||
&end_para();
|
||||
print TEMP "<P>\n";
|
||||
$inpara = 1;
|
||||
}
|
||||
|
||||
|
||||
# Main program
|
||||
|
||||
$innf = 0;
|
||||
$inpara = 0;
|
||||
$inpre = 0;
|
||||
$wrotetext = 0;
|
||||
$toc = 0;
|
||||
$ref = 1;
|
||||
|
||||
while ($#ARGV >= 0 && $ARGV[0] =~ /^-/)
|
||||
{
|
||||
$toc = 1 if $ARGV[0] eq "-toc";
|
||||
shift;
|
||||
}
|
||||
|
||||
# Initial output to STDOUT
|
||||
|
||||
print <<End ;
|
||||
<html>
|
||||
<head>
|
||||
<title>$ARGV[0] specification</title>
|
||||
</head>
|
||||
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
|
||||
<h1>$ARGV[0] man page</h1>
|
||||
<p>
|
||||
Return to the <a href="index.html">PCRE2 index page</a>.
|
||||
</p>
|
||||
<p>
|
||||
This page is part of the PCRE2 HTML documentation. It was generated
|
||||
automatically from the original man page. If there is any nonsense in it,
|
||||
please consult the man page, in case the conversion went wrong.
|
||||
<br>
|
||||
End
|
||||
|
||||
print "<ul>\n" if ($toc);
|
||||
|
||||
open(TEMP, ">/tmp/$$") || die "Can't open /tmp/$$ for output\n";
|
||||
|
||||
while (<STDIN>)
|
||||
{
|
||||
# Handle lines beginning with a dot
|
||||
|
||||
if (/^\./)
|
||||
{
|
||||
# Some of the PCRE2 man pages used to contain instances of .br. However,
|
||||
# they should have all been removed because they cause trouble in some
|
||||
# (other) automated systems that translate man pages to HTML. Complain if
|
||||
# we find .br or .in (another macro that is deprecated).
|
||||
|
||||
if (/^\.br/ || /^\.in/)
|
||||
{
|
||||
print STDERR "\n*** Deprecated macro encountered - rewrite needed\n";
|
||||
print STDERR "*** $_\n";
|
||||
die "*** Processing abandoned\n";
|
||||
}
|
||||
|
||||
# Instead of .br, relevent "literal" sections are enclosed in .nf/.fi.
|
||||
|
||||
elsif (/^\.nf/)
|
||||
{
|
||||
$innf = 1;
|
||||
}
|
||||
|
||||
elsif (/^\.fi/)
|
||||
{
|
||||
$innf = 0;
|
||||
}
|
||||
|
||||
# Handling .sp is subtle. If it is inside a literal section, do nothing if
|
||||
# the next line is a non literal text line; similarly, if not inside a
|
||||
# literal section, do nothing if a literal follows, unless we are inside
|
||||
# a .nf/.ne section. The point being that the <pre> and </pre> that delimit
|
||||
# literal sections will do the spacing. Always skip if no previous output.
|
||||
|
||||
elsif (/^\.sp/)
|
||||
{
|
||||
if ($wrotetext)
|
||||
{
|
||||
$_ = <STDIN>;
|
||||
if ($inpre)
|
||||
{
|
||||
print TEMP "\n" if (/^[\s.]/);
|
||||
}
|
||||
else
|
||||
{
|
||||
print TEMP "<br>\n<br>\n" if ($innf || !/^[\s.]/);
|
||||
}
|
||||
redo; # Now process the lookahead line we just read
|
||||
}
|
||||
}
|
||||
elsif (/^\.TP/ || /^\.PP/ || /^\.P/)
|
||||
{
|
||||
&new_para();
|
||||
}
|
||||
elsif (/^\.SH\s*("?)(.*)\1/)
|
||||
{
|
||||
# Ignore the NAME section
|
||||
if ($2 =~ /^NAME\b/)
|
||||
{
|
||||
<STDIN>;
|
||||
next;
|
||||
}
|
||||
|
||||
&end_para();
|
||||
my($title) = &do_line($2);
|
||||
if ($toc)
|
||||
{
|
||||
printf("<li><a name=\"TOC%d\" href=\"#SEC%d\">$title</a>\n",
|
||||
$ref, $ref);
|
||||
printf TEMP ("<br><a name=\"SEC%d\" href=\"#TOC1\">$title</a><br>\n",
|
||||
$ref, $ref);
|
||||
$ref++;
|
||||
}
|
||||
else
|
||||
{
|
||||
print TEMP "<br><b>\n$title\n</b><br>\n";
|
||||
}
|
||||
}
|
||||
elsif (/^\.SS\s*("?)(.*)\1/)
|
||||
{
|
||||
&end_para();
|
||||
my($title) = &do_line($2);
|
||||
print TEMP "<br><b>\n$title\n</b><br>\n";
|
||||
}
|
||||
elsif (/^\.B\s*(.*)/)
|
||||
{
|
||||
&new_para() if (!$inpara);
|
||||
$_ = &do_line($1);
|
||||
s/"(.*?)"/$1/g;
|
||||
print TEMP "<b>$_</b>\n";
|
||||
$wrotetext = 1;
|
||||
}
|
||||
elsif (/^\.I\s*(.*)/)
|
||||
{
|
||||
&new_para() if (!$inpara);
|
||||
$_ = &do_line($1);
|
||||
s/"(.*?)"/$1/g;
|
||||
print TEMP "<i>$_</i>\n";
|
||||
$wrotetext = 1;
|
||||
}
|
||||
|
||||
# A comment that starts "HREF" takes the next line as a name that
|
||||
# is turned into a hyperlink, using the text given, which might be
|
||||
# in a special font. If it ends in () or (digits) or punctuation, they
|
||||
# aren't part of the link.
|
||||
|
||||
elsif (/^\.\\"\s*HREF/)
|
||||
{
|
||||
$_=<STDIN>;
|
||||
chomp;
|
||||
$_ = &do_line($_);
|
||||
$_ =~ s/\s+$//;
|
||||
$_ =~ /^(?:<.>)?([^<(]+)(?:\(\))?(?:<\/.>)?(?:\(\d+\))?[.,;:]?$/;
|
||||
print TEMP "<a href=\"$1.html\">$_</a>\n";
|
||||
}
|
||||
|
||||
# A comment that starts "HTML" inserts literal HTML
|
||||
|
||||
elsif (/^\.\\"\s*HTML\s*(.*)/)
|
||||
{
|
||||
print TEMP $1;
|
||||
}
|
||||
|
||||
# A comment that starts < inserts that HTML at the end of the
|
||||
# *next* input line - so as not to get a newline between them.
|
||||
|
||||
elsif (/^\.\\"\s*(<.*>)/)
|
||||
{
|
||||
my($markup) = $1;
|
||||
$_=<STDIN>;
|
||||
chomp;
|
||||
$_ = &do_line($_);
|
||||
$_ =~ s/\s+$//;
|
||||
print TEMP "$_$markup\n";
|
||||
}
|
||||
|
||||
# A comment that starts JOIN joins the next two lines together, with one
|
||||
# space between them. Then that line is processed. This is used in some
|
||||
# displays where two lines are needed for the "man" version. JOINSH works
|
||||
# the same, except that it assumes this is a shell command, so removes
|
||||
# continuation backslashes.
|
||||
|
||||
elsif (/^\.\\"\s*JOIN(SH)?/)
|
||||
{
|
||||
my($one,$two);
|
||||
$one = <STDIN>;
|
||||
$two = <STDIN>;
|
||||
$one =~ s/\s*\\e\s*$// if (defined($1));
|
||||
chomp($one);
|
||||
$two =~ s/^\s+//;
|
||||
$_ = "$one $two";
|
||||
redo; # Process the joined lines
|
||||
}
|
||||
|
||||
# .EX/.EE are used in the pcredemo page to bracket the entire program,
|
||||
# which is unmodified except for turning backslash into "\e".
|
||||
|
||||
elsif (/^\.EX\s*$/)
|
||||
{
|
||||
print TEMP "<PRE>\n";
|
||||
while (<STDIN>)
|
||||
{
|
||||
last if /^\.EE\s*$/;
|
||||
s/\\e/\\/g;
|
||||
s/&/&/g;
|
||||
s/</</g;
|
||||
s/>/>/g;
|
||||
print TEMP;
|
||||
}
|
||||
}
|
||||
|
||||
# Ignore anything not recognized
|
||||
|
||||
next;
|
||||
}
|
||||
|
||||
# Line does not begin with a dot. Replace blank lines with new paragraphs
|
||||
|
||||
if (/^\s*$/)
|
||||
{
|
||||
&end_para() if ($wrotetext);
|
||||
next;
|
||||
}
|
||||
|
||||
# Convert fonts changes and output an ordinary line. Ensure that indented
|
||||
# lines are marked as literal.
|
||||
|
||||
$_ = &do_line($_);
|
||||
&new_para() if (!$inpara);
|
||||
|
||||
if (/^\s/)
|
||||
{
|
||||
if (!$inpre)
|
||||
{
|
||||
print TEMP "<pre>\n";
|
||||
$inpre = 1;
|
||||
}
|
||||
}
|
||||
elsif ($inpre)
|
||||
{
|
||||
print TEMP "</pre>\n";
|
||||
$inpre = 0;
|
||||
}
|
||||
|
||||
# Add <br> to the end of a non-literal line if we are within .nf/.fi
|
||||
|
||||
$_ .= "<br>\n" if (!$inpre && $innf);
|
||||
|
||||
print TEMP;
|
||||
$wrotetext = 1;
|
||||
}
|
||||
|
||||
# The TOC, if present, will have been written - terminate it
|
||||
|
||||
print "</ul>\n" if ($toc);
|
||||
|
||||
# Copy the remainder to the standard output
|
||||
|
||||
close(TEMP);
|
||||
open(TEMP, "/tmp/$$") || die "Can't open /tmp/$$ for input\n";
|
||||
|
||||
print while (<TEMP>);
|
||||
|
||||
print <<End ;
|
||||
<p>
|
||||
Return to the <a href="index.html">PCRE2 index page</a>.
|
||||
</p>
|
||||
End
|
||||
|
||||
close(TEMP);
|
||||
unlink("/tmp/$$");
|
||||
|
||||
# End
|
||||
|
|
@ -0,0 +1,67 @@
|
|||
#! /usr/bin/perl
|
||||
|
||||
# A script to scan PCRE2's man pages to check for typos in the control
|
||||
# sequences. I use only a small set of the available repertoire, so it is
|
||||
# straightforward to check that nothing else has slipped in by mistake. This
|
||||
# script should be called in the doc directory.
|
||||
|
||||
$yield = 0;
|
||||
|
||||
while (scalar(@ARGV) > 0)
|
||||
{
|
||||
$line = 0;
|
||||
$file = shift @ARGV;
|
||||
|
||||
open (IN, $file) || die "Failed to open $file\n";
|
||||
|
||||
while (<IN>)
|
||||
{
|
||||
$line++;
|
||||
if (/^\s*$/)
|
||||
{
|
||||
printf "Empty line $line of $file\n";
|
||||
$yield = 1;
|
||||
}
|
||||
elsif (/^\./)
|
||||
{
|
||||
if (!/^\.\s*$|
|
||||
^\.B\s+\S|
|
||||
^\.TH\s\S|
|
||||
^\.SH\s\S|
|
||||
^\.SS\s\S|
|
||||
^\.TP(?:\s?\d+)?\s*$|
|
||||
^\.SM\s*$|
|
||||
^\.br\s*$|
|
||||
^\.rs\s*$|
|
||||
^\.sp\s*$|
|
||||
^\.nf\s*$|
|
||||
^\.fi\s*$|
|
||||
^\.P\s*$|
|
||||
^\.PP\s*$|
|
||||
^\.\\"(?:\ HREF)?\s*$|
|
||||
^\.\\"\sHTML\s<a\shref="[^"]+?">\s*$|
|
||||
^\.\\"\sHTML\s<a\sname="[^"]+?"><\/a>\s*$|
|
||||
^\.\\"\s<\/a>\s*$|
|
||||
^\.\\"\sJOINSH\s*$|
|
||||
^\.\\"\sJOIN\s*$/x
|
||||
)
|
||||
{
|
||||
printf "Bad control line $line of $file\n";
|
||||
$yield = 1;
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
if (/\\[^ef]|\\f[^IBP]/)
|
||||
{
|
||||
printf "Bad backslash in line $line of $file\n";
|
||||
$yield = 1;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
close(IN);
|
||||
}
|
||||
|
||||
exit $yield;
|
||||
# End
|
||||
|
|
@ -0,0 +1,113 @@
|
|||
#! /usr/bin/perl -w
|
||||
|
||||
# Script to take the output of nroff -man and remove all the backspacing and
|
||||
# the page footers and the screen commands etc so that it is more usefully
|
||||
# readable online. In fact, in the latest nroff, intermediate footers don't
|
||||
# seem to be generated any more.
|
||||
|
||||
$blankcount = 0;
|
||||
$lastwascut = 0;
|
||||
$firstheader = 1;
|
||||
|
||||
# Input on STDIN; output to STDOUT.
|
||||
|
||||
while (<STDIN>)
|
||||
{
|
||||
s/\x1b\[\d+m//g; # Remove screen controls "ESC [ number m"
|
||||
s/.\x8//g; # Remove "char, backspace"
|
||||
|
||||
# Handle header lines. Retain only the first one we encounter, but remove
|
||||
# the blank line that follows. Any others (e.g. at end of document) and the
|
||||
# following blank line are dropped.
|
||||
|
||||
if (/^PCRE(\w*)\(([13])\)\s+PCRE\1\(\2\)$/)
|
||||
{
|
||||
if ($firstheader)
|
||||
{
|
||||
$firstheader = 0;
|
||||
print;
|
||||
$lastprinted = $_;
|
||||
$lastwascut = 0;
|
||||
}
|
||||
$_=<STDIN>; # Remove a blank that follows
|
||||
next;
|
||||
}
|
||||
|
||||
# Count runs of empty lines
|
||||
|
||||
if (/^\s*$/)
|
||||
{
|
||||
$blankcount++;
|
||||
$lastwascut = 0;
|
||||
next;
|
||||
}
|
||||
|
||||
# If a chunk of lines has been cut out (page footer) and the next line
|
||||
# has a different indentation, put back one blank line.
|
||||
|
||||
if ($lastwascut && $blankcount < 1 && defined($lastprinted))
|
||||
{
|
||||
($a) = $lastprinted =~ /^(\s*)/;
|
||||
($b) = $_ =~ /^(\s*)/;
|
||||
$blankcount++ if ($a ne $b);
|
||||
}
|
||||
|
||||
# We get here only when we have a non-blank line in hand. If it was preceded
|
||||
# by 3 or more blank lines, read the next 3 lines and see if they are blank.
|
||||
# If so, remove all 7 lines, and remember that we have just done a cut.
|
||||
|
||||
if ($blankcount >= 3)
|
||||
{
|
||||
for ($i = 0; $i < 3; $i++)
|
||||
{
|
||||
$next[$i] = <STDIN>;
|
||||
$next[$i] = "" if !defined $next[$i];
|
||||
$next[$i] =~ s/\x1b\[\d+m//g; # Remove screen controls "ESC [ number m"
|
||||
$next[$i] =~ s/.\x8//g; # Remove "char, backspace"
|
||||
}
|
||||
|
||||
# Cut out chunks of the form <3 blanks><non-blank><3 blanks>
|
||||
|
||||
if ($next[0] =~ /^\s*$/ &&
|
||||
$next[1] =~ /^\s*$/ &&
|
||||
$next[2] =~ /^\s*$/)
|
||||
{
|
||||
$blankcount -= 3;
|
||||
$lastwascut = 1;
|
||||
}
|
||||
|
||||
# Otherwise output the saved blanks, the current, and the next three
|
||||
# lines. Remember the last printed line.
|
||||
|
||||
else
|
||||
{
|
||||
for ($i = 0; $i < $blankcount; $i++) { print "\n"; }
|
||||
print;
|
||||
for ($i = 0; $i < 3; $i++)
|
||||
{
|
||||
$next[$i] =~ s/.\x8//g;
|
||||
print $next[$i];
|
||||
$lastprinted = $_;
|
||||
}
|
||||
$lastwascut = 0;
|
||||
$blankcount = 0;
|
||||
}
|
||||
}
|
||||
|
||||
# This non-blank line is not preceded by 3 or more blank lines. Output
|
||||
# any blanks there are, and the line. Remember it. Force two blank lines
|
||||
# before headings.
|
||||
|
||||
else
|
||||
{
|
||||
$blankcount = 2 if /^\S/ && !/^Last updated/ && !/^Copyright/ &&
|
||||
defined($lastprinted);
|
||||
for ($i = 0; $i < $blankcount; $i++) { print "\n"; }
|
||||
print;
|
||||
$lastprinted = $_;
|
||||
$lastwascut = 0;
|
||||
$blankcount = 0;
|
||||
}
|
||||
}
|
||||
|
||||
# End
|
||||
|
|
@ -0,0 +1,35 @@
|
|||
#!/usr/bin/perl
|
||||
|
||||
# This is a script for removing trailing whitespace from lines in files that
|
||||
# are listed on the command line.
|
||||
|
||||
# This subroutine does the work for one file.
|
||||
|
||||
sub detrail {
|
||||
my($file) = $_[0];
|
||||
my($changed) = 0;
|
||||
open(IN, "$file") || die "Can't open $file for input";
|
||||
@lines = <IN>;
|
||||
close(IN);
|
||||
foreach (@lines)
|
||||
{
|
||||
if (/\s+\n$/)
|
||||
{
|
||||
s/\s+\n$/\n/;
|
||||
$changed = 1;
|
||||
}
|
||||
}
|
||||
if ($changed)
|
||||
{
|
||||
open(OUT, ">$file") || die "Can't open $file for output";
|
||||
print OUT @lines;
|
||||
close(OUT);
|
||||
}
|
||||
}
|
||||
|
||||
# This is the main program
|
||||
|
||||
$, = ""; # Output field separator
|
||||
for ($i = 0; $i < @ARGV; $i++) { &detrail($ARGV[$i]); }
|
||||
|
||||
# End
|
||||
|
|
@ -0,0 +1,265 @@
|
|||
#/bin/sh
|
||||
|
||||
# Script to prepare the files for building a PCRE2 release. It does some
|
||||
# processing of the documentation, detrails files, and creates pcre2.h.generic
|
||||
# and config.h.generic (for use by builders who can't run ./configure).
|
||||
|
||||
# You must run this script before runnning "make dist". If its first argument
|
||||
# is "doc", it stops after preparing the documentation. There are no other
|
||||
# arguments. The script makes use of the following files:
|
||||
|
||||
# 132html A Perl script that converts a .1 or .3 man page into HTML. It
|
||||
# "knows" the relevant troff constructs that are used in the PCRE2
|
||||
# man pages.
|
||||
|
||||
# CheckMan A Perl script that checks man pages for typos in the mark up.
|
||||
|
||||
# CleanTxt A Perl script that cleans up the output of "nroff -man" by
|
||||
# removing backspaces and other redundant text so as to produce
|
||||
# a readable .txt file.
|
||||
|
||||
# Detrail A Perl script that removes trailing spaces from files.
|
||||
|
||||
# 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
|
||||
# doc/html can be deleted and re-created from scratch.
|
||||
|
||||
# README & NON-AUTOTOOLS-BUILD
|
||||
# These files are copied into the doc/html directory, with .txt
|
||||
# extensions so that they can by hyperlinked from the HTML
|
||||
# documentation, because some people just go to the HTML without
|
||||
# looking for text files.
|
||||
|
||||
|
||||
# First, sort out the documentation. Remove pcre2demo.3 first because it won't
|
||||
# pass the markup check (it is created below, using markup that none of the
|
||||
# other pages use).
|
||||
|
||||
cd doc
|
||||
echo Processing documentation
|
||||
|
||||
/bin/rm -f pcre2demo.3
|
||||
|
||||
# Check the remaining man pages
|
||||
|
||||
perl ../CheckMan *.1 *.3
|
||||
if [ $? != 0 ] ; then exit 1; fi
|
||||
|
||||
# Make Text form of the documentation. It needs some mangling to make it
|
||||
# tidy for online reading. Concatenate all the .3 stuff, but omit the
|
||||
# individual function pages.
|
||||
|
||||
cat <<End >pcre2.txt
|
||||
-----------------------------------------------------------------------------
|
||||
This file contains a concatenation of the PCRE2 man pages, converted to plain
|
||||
text format for ease of searching with a text editor, or for use on systems
|
||||
that do not have a man page processor. The small individual files that give
|
||||
synopses of each function in the library have not been included. Neither has
|
||||
the pcre2demo program. There are separate text files for the pcre2grep and
|
||||
pcre2test commands.
|
||||
-----------------------------------------------------------------------------
|
||||
|
||||
|
||||
End
|
||||
|
||||
echo "Making pcre2.txt"
|
||||
for file in pcre2api pcre2callout pcre2unicode ; do
|
||||
|
||||
#for file in pcre pcre16 pcre32 pcrebuild pcrematching \
|
||||
# pcrecompat pcrepattern pcresyntax pcrejit pcrepartial \
|
||||
# pcreprecompile pcreperform pcreposix pcrecpp pcresample \
|
||||
# pcrelimits pcrestack ; do
|
||||
|
||||
echo " Processing $file.3"
|
||||
nroff -c -man $file.3 >$file.rawtxt
|
||||
perl ../CleanTxt <$file.rawtxt >>pcre2.txt
|
||||
/bin/rm $file.rawtxt
|
||||
echo "------------------------------------------------------------------------------" >>pcre2.txt
|
||||
if [ "$file" != "pcre2sample" ] ; then
|
||||
echo " " >>pcre2.txt
|
||||
echo " " >>pcre2.txt
|
||||
fi
|
||||
done
|
||||
|
||||
# The three commands
|
||||
for file in pcre2test ; do
|
||||
# for file in pcre2test pcre2grep pcre-config ; do
|
||||
echo Making $file.txt
|
||||
nroff -c -man $file.1 >$file.rawtxt
|
||||
perl ../CleanTxt <$file.rawtxt >$file.txt
|
||||
/bin/rm $file.rawtxt
|
||||
done
|
||||
|
||||
|
||||
# Make pcre2demo.3 from the pcre2demo.c source file
|
||||
|
||||
echo "Making pcre2demo.3"
|
||||
perl <<"END" >pcre2demo.3
|
||||
open(IN, "../src/pcre2demo.c") || die "Failed to open src/pcre2demo.c\n";
|
||||
open(OUT, ">pcre2demo.3") || die "Failed to open pcre2demo.3\n";
|
||||
print OUT ".\\\" Start example.\n" .
|
||||
".de EX\n" .
|
||||
". nr mE \\\\n(.f\n" .
|
||||
". nf\n" .
|
||||
". nh\n" .
|
||||
". ft CW\n" .
|
||||
"..\n" .
|
||||
".\n" .
|
||||
".\n" .
|
||||
".\\\" End example.\n" .
|
||||
".de EE\n" .
|
||||
". ft \\\\n(mE\n" .
|
||||
". fi\n" .
|
||||
". hy \\\\n(HY\n" .
|
||||
"..\n" .
|
||||
".\n" .
|
||||
".EX\n" ;
|
||||
while (<IN>)
|
||||
{
|
||||
s/\\/\\e/g;
|
||||
print OUT;
|
||||
}
|
||||
print OUT ".EE\n";
|
||||
close(IN);
|
||||
close(OUT);
|
||||
END
|
||||
if [ $? != 0 ] ; then exit 1; fi
|
||||
|
||||
|
||||
# Make HTML form of the documentation.
|
||||
|
||||
echo "Making HTML documentation"
|
||||
/bin/rm html/*
|
||||
cp index.html.src html/index.html
|
||||
cp ../README html/README.txt
|
||||
# cp ../NON-AUTOTOOLS-BUILD html/NON-AUTOTOOLS-BUILD.txt
|
||||
|
||||
for file in *.1 ; do
|
||||
base=`basename $file .1`
|
||||
echo " Making $base.html"
|
||||
perl ../132html -toc $base <$file >html/$base.html
|
||||
done
|
||||
|
||||
# Exclude table of contents for function summaries. It seems that expr
|
||||
# forces an anchored regex. Also exclude them for small pages that have
|
||||
# only one section.
|
||||
|
||||
for file in *.3 ; do
|
||||
base=`basename $file .3`
|
||||
toc=-toc
|
||||
if [ `expr $base : '.*_'` -ne 0 ] ; then toc="" ; fi
|
||||
if [ "$base" = "pcre2sample" ] || \
|
||||
[ "$base" = "pcre2stack" ] || \
|
||||
[ "$base" = "pcre2compat" ] || \
|
||||
[ "$base" = "pcre2limits" ] || \
|
||||
[ "$base" = "pcre2perform" ] || \
|
||||
[ "$base" = "pcre2unicode" ] ; then
|
||||
toc=""
|
||||
fi
|
||||
echo " Making $base.html"
|
||||
perl ../132html $toc $base <$file >html/$base.html
|
||||
if [ $? != 0 ] ; then exit 1; fi
|
||||
done
|
||||
|
||||
# End of documentation processing; stop if only documentation required.
|
||||
|
||||
cd ..
|
||||
echo Documentation done
|
||||
if [ "$1" = "doc" ] ; then exit; fi
|
||||
|
||||
# FIXME pro tem only do docs
|
||||
exit
|
||||
|
||||
# These files are detrailed; do not detrail the test data because there may be
|
||||
# significant trailing spaces. Do not detrail RunTest.bat, because it has CRLF
|
||||
# line endings and the detrail script removes all trailing white space. The
|
||||
# configure files are also omitted from the detrailing. We don't bother with
|
||||
# those pcre[16|32]_xx files that just define COMPILE_PCRE16 and then #include the
|
||||
# common file, because they aren't going to change.
|
||||
|
||||
files="\
|
||||
Makefile.am \
|
||||
Makefile.in \
|
||||
configure.ac \
|
||||
README \
|
||||
LICENCE \
|
||||
COPYING \
|
||||
AUTHORS \
|
||||
NEWS \
|
||||
NON-UNIX-USE \
|
||||
NON-AUTOTOOLS-BUILD \
|
||||
INSTALL \
|
||||
132html \
|
||||
CleanTxt \
|
||||
Detrail \
|
||||
ChangeLog \
|
||||
CMakeLists.txt \
|
||||
RunGrepTest \
|
||||
RunTest \
|
||||
pcre-config.in \
|
||||
libpcre.pc.in \
|
||||
libpcre16.pc.in \
|
||||
libpcre32.pc.in \
|
||||
libpcreposix.pc.in \
|
||||
libpcrecpp.pc.in \
|
||||
config.h.in \
|
||||
pcre_chartables.c.dist \
|
||||
pcredemo.c \
|
||||
pcregrep.c \
|
||||
pcretest.c \
|
||||
dftables.c \
|
||||
pcreposix.c \
|
||||
pcreposix.h \
|
||||
pcre.h.in \
|
||||
pcre_internal.h \
|
||||
pcre_byte_order.c \
|
||||
pcre_compile.c \
|
||||
pcre_config.c \
|
||||
pcre_dfa_exec.c \
|
||||
pcre_exec.c \
|
||||
pcre_fullinfo.c \
|
||||
pcre_get.c \
|
||||
pcre_globals.c \
|
||||
pcre_jit_compile.c \
|
||||
pcre_jit_test.c \
|
||||
pcre_maketables.c \
|
||||
pcre_newline.c \
|
||||
pcre_ord2utf8.c \
|
||||
pcre16_ord2utf16.c \
|
||||
pcre32_ord2utf32.c \
|
||||
pcre_printint.c \
|
||||
pcre_refcount.c \
|
||||
pcre_string_utils.c \
|
||||
pcre_study.c \
|
||||
pcre_tables.c \
|
||||
pcre_valid_utf8.c \
|
||||
pcre_version.c \
|
||||
pcre_xclass.c \
|
||||
pcre16_utf16_utils.c \
|
||||
pcre32_utf32_utils.c \
|
||||
pcre16_valid_utf16.c \
|
||||
pcre32_valid_utf32.c \
|
||||
pcre_scanner.cc \
|
||||
pcre_scanner.h \
|
||||
pcre_scanner_unittest.cc \
|
||||
pcrecpp.cc \
|
||||
pcrecpp.h \
|
||||
pcrecpparg.h.in \
|
||||
pcrecpp_unittest.cc \
|
||||
pcre_stringpiece.cc \
|
||||
pcre_stringpiece.h.in \
|
||||
pcre_stringpiece_unittest.cc \
|
||||
perltest.pl \
|
||||
ucp.h \
|
||||
makevp.bat \
|
||||
pcre.def \
|
||||
libpcre.def \
|
||||
libpcreposix.def"
|
||||
|
||||
echo Detrailing
|
||||
perl ./Detrail $files doc/p* doc/html/*
|
||||
|
||||
echo Done
|
||||
|
||||
#End
|
||||
|
|
@ -0,0 +1 @@
|
|||
This is a placeholder README file for a work in progress.
|
||||
|
|
@ -0,0 +1,177 @@
|
|||
<html>
|
||||
<!-- This is a manually maintained file that is the root of the HTML version of
|
||||
the PCRE2 documentation. When the HTML documents are built from the man
|
||||
page versions, the entire doc/html directory is emptied, this file is then
|
||||
copied into doc/html/index.html, and the remaining files therein are
|
||||
created by the 132html script.
|
||||
-->
|
||||
<head>
|
||||
<title>PCRE2 specification</title>
|
||||
</head>
|
||||
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
|
||||
<h1>Perl-compatible Regular Expressions (revised API: PCRE2)</h1>
|
||||
<p>
|
||||
The HTML documentation for PCRE2 consists of a number of pages that are listed
|
||||
below in alphabetical order. If you are new to PCRE2, please read the first one
|
||||
first.
|
||||
</p>
|
||||
|
||||
<table>
|
||||
<tr><td><a href="pcre2.html">pcre</a></td>
|
||||
<td> Introductory page</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2-config.html">pcre-config</a></td>
|
||||
<td> Information about the installation configuration</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2api.html">pcreapi</a></td>
|
||||
<td> PCRE2's native API</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2build.html">pcrebuild</a></td>
|
||||
<td> Building PCRE2</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2callout.html">pcre2callout</a></td>
|
||||
<td> The <i>callout</i> facility</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2compat.html">pcre2compat</a></td>
|
||||
<td> Compability with Perl</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2demo.html">pcre2demo</a></td>
|
||||
<td> A demonstration C program that uses the PCRE2 library</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2grep.html">pcre2grep</a></td>
|
||||
<td> The <b>pcre2grep</b> command</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2jit.html">pcre2jit</a></td>
|
||||
<td> Discussion of the just-in-time optimization support</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2limits.html">pcre2limits</a></td>
|
||||
<td> Details of size and other limits</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2matching.html">pcre2matching</a></td>
|
||||
<td> Discussion of the two matching algorithms</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2partial.html">pcre2partial</a></td>
|
||||
<td> Using PCRE2 for partial matching</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2pattern.html">pcre2pattern</a></td>
|
||||
<td> Specification of the regular expressions supported by PCRE2</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2perform.html">pcre2perform</a></td>
|
||||
<td> Some comments on performance</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2posix.html">pcre2posix</a></td>
|
||||
<td> The POSIX API to the PCRE2 8-bit library</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2precompile.html">pcre2precompile</a></td>
|
||||
<td> How to save and re-use compiled patterns</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2sample.html">pcre2sample</a></td>
|
||||
<td> Discussion of the pcre2demo program</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2stack.html">pcre2stack</a></td>
|
||||
<td> Discussion of PCRE2's stack usage</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2syntax.html">pcre2syntax</a></td>
|
||||
<td> Syntax quick-reference summary</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2test.html">pcre2test</a></td>
|
||||
<td> The <b>pcre2test</b> command for testing PCRE2</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2unicode.html">pcre2unicode</a></td>
|
||||
<td> Discussion of Unicode and UTF-8/UTF-16/UTF-32 support</td></tr>
|
||||
</table>
|
||||
|
||||
<p>
|
||||
There are also individual pages that summarize the interface for each function
|
||||
in the library. There is a single page for each triple of 8-bit/16-bit/32-bit
|
||||
functions.
|
||||
</p>
|
||||
|
||||
<table>
|
||||
|
||||
<tr><td><a href="pcre2_assign_jit_stack.html">pcre2_assign_jit_stack</a></td>
|
||||
<td> Assign stack for JIT matching</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_compile.html">pcre2_compile</a></td>
|
||||
<td> Compile a regular expression</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_compile2.html">pcre2_compile2</a></td>
|
||||
<td> Compile a regular expression (alternate interface)</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_config.html">pcre2_config</a></td>
|
||||
<td> Show build-time configuration options</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_copy_named_substring.html">pcre2_copy_named_substring</a></td>
|
||||
<td> Extract named substring into given buffer</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_copy_substring.html">pcre2_copy_substring</a></td>
|
||||
<td> Extract numbered substring into given buffer</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_dfa_exec.html">pcre2_dfa_exec</a></td>
|
||||
<td> Match a compiled pattern to a subject string
|
||||
(DFA algorithm; <i>not</i> Perl compatible)</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_exec.html">pcre2_exec</a></td>
|
||||
<td> Match a compiled pattern to a subject string
|
||||
(Perl compatible)</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_free_study.html">pcre2_free_study</a></td>
|
||||
<td> Free study data</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_free_substring.html">pcre2_free_substring</a></td>
|
||||
<td> Free extracted substring</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_free_substring_list.html">pcre2_free_substring_list</a></td>
|
||||
<td> Free list of extracted substrings</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_fullinfo.html">pcre2_fullinfo</a></td>
|
||||
<td> Extract information about a pattern</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_get_named_substring.html">pcre2_get_named_substring</a></td>
|
||||
<td> Extract named substring into new memory</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_get_stringnumber.html">pcre2_get_stringnumber</a></td>
|
||||
<td> Convert captured string name to number</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_get_stringtable_entries.html">pcre2_get_stringtable_entries</a></td>
|
||||
<td> Find table entries for given string name</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_get_substring.html">pcre2_get_substring</a></td>
|
||||
<td> Extract numbered substring into new memory</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_get_substring_list.html">pcre2_get_substring_list</a></td>
|
||||
<td> Extract all substrings into new memory</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_jit_exec.html">pcre2_jit_exec</a></td>
|
||||
<td> Fast path interface to JIT matching</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_jit_stack_alloc.html">pcre2_jit_stack_alloc</a></td>
|
||||
<td> Create a stack for JIT matching</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_jit_stack_free.html">pcre2_jit_stack_free</a></td>
|
||||
<td> Free a JIT matching stack</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_maketables.html">pcre2_maketables</a></td>
|
||||
<td> Build character tables in current locale</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_pattern_to_host_byte_order.html">pcre2_pattern_to_host_byte_order</a></td>
|
||||
<td> Convert compiled pattern to host byte order if necessary</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_refcount.html">pcre2_refcount</a></td>
|
||||
<td> Maintain reference count in compiled pattern</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_study.html">pcre2_study</a></td>
|
||||
<td> Study a compiled pattern</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_utf16_to_host_byte_order.html">pcre2_utf16_to_host_byte_order</a></td>
|
||||
<td> Convert UTF-16 string to host byte order if necessary</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_utf32_to_host_byte_order.html">pcre2_utf32_to_host_byte_order</a></td>
|
||||
<td> Convert UTF-32 string to host byte order if necessary</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_version.html">pcre2_version</a></td>
|
||||
<td> Return PCRE2 version and release date</td></tr>
|
||||
</table>
|
||||
|
||||
</html>
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,270 @@
|
|||
<html>
|
||||
<head>
|
||||
<title>pcre2callout specification</title>
|
||||
</head>
|
||||
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
|
||||
<h1>pcre2callout man page</h1>
|
||||
<p>
|
||||
Return to the <a href="index.html">PCRE2 index page</a>.
|
||||
</p>
|
||||
<p>
|
||||
This page is part of the PCRE2 HTML documentation. It was generated
|
||||
automatically from the original man page. If there is any nonsense in it,
|
||||
please consult the man page, in case the conversion went wrong.
|
||||
<br>
|
||||
<ul>
|
||||
<li><a name="TOC1" href="#SEC1">SYNOPSIS</a>
|
||||
<li><a name="TOC2" href="#SEC2">DESCRIPTION</a>
|
||||
<li><a name="TOC3" href="#SEC3">MISSING CALLOUTS</a>
|
||||
<li><a name="TOC4" href="#SEC4">THE CALLOUT INTERFACE</a>
|
||||
<li><a name="TOC5" href="#SEC5">RETURN VALUES</a>
|
||||
<li><a name="TOC6" href="#SEC6">AUTHOR</a>
|
||||
<li><a name="TOC7" href="#SEC7">REVISION</a>
|
||||
</ul>
|
||||
<br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br>
|
||||
<P>
|
||||
<b>#include <pcre2.h></b>
|
||||
</P>
|
||||
<P>
|
||||
<b>int (*pcre2_callout)(pcre2_callout_block *);</b>
|
||||
</P>
|
||||
<br><a name="SEC2" href="#TOC1">DESCRIPTION</a><br>
|
||||
<P>
|
||||
PCRE2 provides a feature called "callout", which is a means of temporarily
|
||||
passing control to the caller of PCRE2 in the middle of pattern matching. The
|
||||
caller of PCRE2 provides an external function by putting its entry point in
|
||||
a match context (see <b>pcre2_set_callout()</b>) in the
|
||||
<a href="pcre2api.html"><b>pcre2api</b></a>
|
||||
documentation).
|
||||
</P>
|
||||
<P>
|
||||
Within a regular expression, (?C) indicates the points at which the external
|
||||
function is to be called. Different callout points can be identified by putting
|
||||
a number less than 256 after the letter C. The default value is zero.
|
||||
For example, this pattern has two callout points:
|
||||
<pre>
|
||||
(?C1)abc(?C2)def
|
||||
</pre>
|
||||
If the PCRE2_AUTO_CALLOUT option bit is set when a pattern is compiled, PCRE2
|
||||
automatically inserts callouts, all with number 255, before each item in the
|
||||
pattern. For example, if PCRE2_AUTO_CALLOUT is used with the pattern
|
||||
<pre>
|
||||
A(\d{2}|--)
|
||||
</pre>
|
||||
it is processed as if it were
|
||||
<br>
|
||||
<br>
|
||||
(?C255)A(?C255)((?C255)\d{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255)
|
||||
<br>
|
||||
<br>
|
||||
Notice that there is a callout before and after each parenthesis and
|
||||
alternation bar. If the pattern contains a conditional group whose condition is
|
||||
an assertion, an automatic callout is inserted immediately before the
|
||||
condition. Such a callout may also be inserted explicitly, for example:
|
||||
<pre>
|
||||
(?(?C9)(?=a)ab|de)
|
||||
</pre>
|
||||
This applies only to assertion conditions (because they are themselves
|
||||
independent groups).
|
||||
</P>
|
||||
<P>
|
||||
Automatic callouts can be used for tracking the progress of pattern matching.
|
||||
The
|
||||
<a href="pcre2test.html"><b>pcre2test</b></a>
|
||||
program has a pattern qualifier (/auto_callout) that sets automatic callouts;
|
||||
when it is used, the output indicates how the pattern is being matched. This is
|
||||
useful information when you are trying to optimize the performance of a
|
||||
particular pattern.
|
||||
</P>
|
||||
<br><a name="SEC3" href="#TOC1">MISSING CALLOUTS</a><br>
|
||||
<P>
|
||||
You should be aware that, because of optimizations in the way PCRE2 compiles
|
||||
and matches patterns, callouts sometimes do not happen exactly as you might
|
||||
expect.
|
||||
</P>
|
||||
<P>
|
||||
At compile time, PCRE2 "auto-possessifies" repeated items when it knows that
|
||||
what follows cannot be part of the repeat. For example, a+[bc] is compiled as
|
||||
if it were a++[bc]. The <b>pcre2test</b> output when this pattern is anchored
|
||||
and then applied with automatic callouts to the string "aaaa" is:
|
||||
<pre>
|
||||
--->aaaa
|
||||
+0 ^ ^
|
||||
+1 ^ a+
|
||||
+3 ^ ^ [bc]
|
||||
No match
|
||||
</pre>
|
||||
This indicates that when matching [bc] fails, there is no backtracking into a+
|
||||
and therefore the callouts that would be taken for the backtracks do not occur.
|
||||
You can disable the auto-possessify feature by passing PCRE2_NO_AUTO_POSSESS
|
||||
to <b>pcre2_compile()</b>, or starting the pattern with (*NO_AUTO_POSSESS). If
|
||||
this is done in <b>pcre2test</b> (using the /no_auto_possess qualifier), the
|
||||
output changes to this:
|
||||
<pre>
|
||||
--->aaaa
|
||||
+0 ^ ^
|
||||
+1 ^ a+
|
||||
+3 ^ ^ [bc]
|
||||
+3 ^ ^ [bc]
|
||||
+3 ^ ^ [bc]
|
||||
+3 ^^ [bc]
|
||||
No match
|
||||
</pre>
|
||||
This time, when matching [bc] fails, the matcher backtracks into a+ and tries
|
||||
again, repeatedly, until a+ itself fails.
|
||||
</P>
|
||||
<P>
|
||||
Other optimizations that provide fast "no match" results also affect callouts.
|
||||
For example, if the pattern is
|
||||
<pre>
|
||||
ab(?C4)cd
|
||||
</pre>
|
||||
PCRE2 knows that any matching string must contain the letter "d". If the
|
||||
subject string is "abyz", the lack of "d" means that matching doesn't ever
|
||||
start, and the callout is never reached. However, with "abyd", though the
|
||||
result is still no match, the callout is obeyed.
|
||||
</P>
|
||||
<P>
|
||||
PCRE2 also knows the minimum length of a matching string, and will immediately
|
||||
give a "no match" return without actually running a match if the subject is not
|
||||
long enough, or, for unanchored patterns, if it has been scanned far enough.
|
||||
</P>
|
||||
<P>
|
||||
You can disable these optimizations by passing the PCRE2_NO_START_OPTIMIZE
|
||||
option to the matching function, or by starting the pattern with
|
||||
(*NO_START_OPT). This slows down the matching process, but does ensure that
|
||||
callouts such as the example above are obeyed.
|
||||
</P>
|
||||
<br><a name="SEC4" href="#TOC1">THE CALLOUT INTERFACE</a><br>
|
||||
<P>
|
||||
During matching, when PCRE2 reaches a callout point, the external function that
|
||||
is set in the match context is called (if it is set). This applies to both
|
||||
normal and DFA matching. The only argument to the callout function is a pointer
|
||||
to a <b>pcre2_callout</b> block. This structure contains the following fields:
|
||||
<pre>
|
||||
uint32_t <i>version</i>;
|
||||
uint32_t <i>callout_number</i>;
|
||||
uint32_t <i>capture_top</i>;
|
||||
uint32_t <i>capture_last</i>;
|
||||
void *<i>callout_data</i>;
|
||||
PCRE2_SIZE *<i>offset_vector</i>;
|
||||
PCRE2_SPTR <i>mark</i>;
|
||||
PCRE2_SPTR <i>subject</i>;
|
||||
PCRE2_SIZE <i>subject_length</i>;
|
||||
PCRE2_SIZE <i>start_match</i>;
|
||||
PCRE2_SIZE <i>current_position</i>;
|
||||
PCRE2_SIZE <i>pattern_position</i>;
|
||||
PCRE2_SIZE <i>next_item_length</i>;
|
||||
</pre>
|
||||
The <i>version</i> field contains the version number of the block format. The
|
||||
current version is 0. The version number will change in future if additional
|
||||
fields are added, but the intention is never to remove any of the existing
|
||||
fields.
|
||||
</P>
|
||||
<P>
|
||||
The <i>callout_number</i> field contains the number of the callout, as compiled
|
||||
into the pattern (that is, the number after ?C for manual callouts, and 255 for
|
||||
automatically generated callouts).
|
||||
</P>
|
||||
<P>
|
||||
The <i>offset_vector</i> field is a pointer to the vector of capturing offsets
|
||||
(the "ovector") that was passed to the matching function in the match data
|
||||
block. When <b>pcre2_match()</b> is used, the contents can be inspected, in
|
||||
order to extract substrings that have been matched so far, in the same way as
|
||||
for extracting substrings after a match has completed. For the DFA matching
|
||||
function, this field is not useful.
|
||||
</P>
|
||||
<P>
|
||||
The <i>subject</i> and <i>subject_length</i> fields contain copies of the values
|
||||
that were passed to the matching function.
|
||||
</P>
|
||||
<P>
|
||||
The <i>start_match</i> field normally contains the offset within the subject at
|
||||
which the current match attempt started. However, if the escape sequence \K
|
||||
has been encountered, this value is changed to reflect the modified starting
|
||||
point. If the pattern is not anchored, the callout function may be called
|
||||
several times from the same point in the pattern for different starting points
|
||||
in the subject.
|
||||
</P>
|
||||
<P>
|
||||
The <i>current_position</i> field contains the offset within the subject of the
|
||||
current match pointer.
|
||||
</P>
|
||||
<P>
|
||||
When the <b>pcre2_match()</b> is used, the <i>capture_top</i> field contains one
|
||||
more than the number of the highest numbered captured substring so far. If no
|
||||
substrings have been captured, the value of <i>capture_top</i> is one. This is
|
||||
always the case when the DFA functions are used, because they do not support
|
||||
captured substrings.
|
||||
</P>
|
||||
<P>
|
||||
The <i>capture_last</i> field contains the number of the most recently captured
|
||||
substring. However, when a recursion exits, the value reverts to what it was
|
||||
outside the recursion, as do the values of all captured substrings. If no
|
||||
substrings have been captured, the value of <i>capture_last</i> is 0. This is
|
||||
always the case for the DFA matching functions.
|
||||
</P>
|
||||
<P>
|
||||
The <i>callout_data</i> field contains a value that is passed to a matching
|
||||
function specifically so that it can be passed back in callouts. It is set in
|
||||
the match context when the callout is set up by calling
|
||||
<b>pcre2_set_callout()</b> (see the
|
||||
<a href="pcre2api.html"><b>pcre2api</b></a>
|
||||
documentation).
|
||||
</P>
|
||||
<P>
|
||||
The <i>pattern_position</i> field contains the offset to the next item to be
|
||||
matched in the pattern string.
|
||||
</P>
|
||||
<P>
|
||||
The <i>next_item_length</i> field contains the length of the next item to be
|
||||
matched in the pattern string. When the callout immediately precedes an
|
||||
alternation bar, a closing parenthesis, or the end of the pattern, the length
|
||||
is zero. When the callout precedes an opening parenthesis, the length is that
|
||||
of the entire subpattern.
|
||||
</P>
|
||||
<P>
|
||||
The <i>pattern_position</i> and <i>next_item_length</i> fields are intended to
|
||||
help in distinguishing between different automatic callouts, which all have the
|
||||
same callout number. However, they are set for all callouts.
|
||||
</P>
|
||||
<P>
|
||||
In callouts from <b>pcre2_match()</b> the <i>mark</i> field contains a pointer to
|
||||
the zero-terminated name of the most recently passed (*MARK), (*PRUNE), or
|
||||
(*THEN) item in the match, or NULL if no such items have been passed. Instances
|
||||
of (*PRUNE) or (*THEN) without a name do not obliterate a previous (*MARK). In
|
||||
callouts from the DFA matching function this field always contains NULL.
|
||||
</P>
|
||||
<br><a name="SEC5" href="#TOC1">RETURN VALUES</a><br>
|
||||
<P>
|
||||
The external callout function returns an integer to PCRE2. If the value is
|
||||
zero, matching proceeds as normal. If the value is greater than zero, matching
|
||||
fails at the current point, but the testing of other matching possibilities
|
||||
goes ahead, just as if a lookahead assertion had failed. If the value is less
|
||||
than zero, the match is abandoned, and the matching function returns the
|
||||
negative value.
|
||||
</P>
|
||||
<P>
|
||||
Negative values should normally be chosen from the set of PCRE2_ERROR_xxx
|
||||
values. In particular, PCRE2_ERROR_NOMATCH forces a standard "no match"
|
||||
failure. The error number PCRE2_ERROR_CALLOUT is reserved for use by callout
|
||||
functions; it will never be used by PCRE2 itself.
|
||||
</P>
|
||||
<br><a name="SEC6" href="#TOC1">AUTHOR</a><br>
|
||||
<P>
|
||||
Philip Hazel
|
||||
<br>
|
||||
University Computing Service
|
||||
<br>
|
||||
Cambridge CB2 3QH, England.
|
||||
<br>
|
||||
</P>
|
||||
<br><a name="SEC7" href="#TOC1">REVISION</a><br>
|
||||
<P>
|
||||
Last updated: 19 October 2014
|
||||
<br>
|
||||
Copyright © 1997-2014 University of Cambridge.
|
||||
<br>
|
||||
<p>
|
||||
Return to the <a href="index.html">PCRE2 index page</a>.
|
||||
</p>
|
||||
|
|
@ -0,0 +1,443 @@
|
|||
<html>
|
||||
<head>
|
||||
<title>pcre2demo specification</title>
|
||||
</head>
|
||||
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
|
||||
<h1>pcre2demo man page</h1>
|
||||
<p>
|
||||
Return to the <a href="index.html">PCRE2 index page</a>.
|
||||
</p>
|
||||
<p>
|
||||
This page is part of the PCRE2 HTML documentation. It was generated
|
||||
automatically from the original man page. If there is any nonsense in it,
|
||||
please consult the man page, in case the conversion went wrong.
|
||||
<br>
|
||||
<ul>
|
||||
</ul>
|
||||
<PRE>
|
||||
/*************************************************
|
||||
* PCRE2 DEMONSTRATION PROGRAM *
|
||||
*************************************************/
|
||||
|
||||
/* This is a demonstration program to illustrate a straightforward way of
|
||||
calling the PCRE2 regular expression library from a C program. See the
|
||||
pcre2sample documentation for a short discussion ("man pcre2sample" if you have
|
||||
the PCRE2 man pages installed). PCRE2 is a revised API for the library, and is
|
||||
incompatible with the original PCRE API.
|
||||
|
||||
There are actually three libraries, each supporting a different code unit
|
||||
width. This demonstration program uses the 8-bit library.
|
||||
|
||||
In Unix-like environments, if PCRE2 is installed in your standard system
|
||||
libraries, you should be able to compile this program using this command:
|
||||
|
||||
gcc -Wall pcre2demo.c -lpcre2-8 -o pcre2demo
|
||||
|
||||
If PCRE2 is not installed in a standard place, it is likely to be installed
|
||||
with support for the pkg-config mechanism. If you have pkg-config, you can
|
||||
compile this program using this command:
|
||||
|
||||
gcc -Wall pcre2demo.c `pkg-config --cflags --libs libpcre2-8` -o pcre2demo
|
||||
|
||||
If you do not have pkg-config, you may have to use this:
|
||||
|
||||
gcc -Wall pcre2demo.c -I/usr/local/include -L/usr/local/lib \
|
||||
-R/usr/local/lib -lpcre2-8 -o pcre2demo
|
||||
|
||||
Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and
|
||||
library files for PCRE2 are installed on your system. Only some operating
|
||||
systems (Solaris is one) use the -R option.
|
||||
|
||||
Building under Windows:
|
||||
|
||||
If you want to statically link this program against a non-dll .a file, you must
|
||||
define PCRE2_STATIC before including pcre2.h, so in this environment, uncomment
|
||||
the following line. */
|
||||
|
||||
/* #define PCRE2_STATIC */
|
||||
|
||||
/* This macro must be defined before including pcre2.h. For a program that uses
|
||||
only one code unit width, it makes it possible to use generic function names
|
||||
such as pcre2_compile(). */
|
||||
|
||||
#define PCRE2_CODE_UNIT_WIDTH 8
|
||||
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
#include <pcre2.h>
|
||||
|
||||
|
||||
/**************************************************************************
|
||||
* Here is the program. The API includes the concept of "contexts" for *
|
||||
* setting up unusual interface requirements for compiling and matching, *
|
||||
* such as custom memory managers and non-standard newline definitions. *
|
||||
* This program does not do any of this, so it makes no use of contexts, *
|
||||
* always passing NULL where a context could be given. *
|
||||
**************************************************************************/
|
||||
|
||||
int main(int argc, char **argv)
|
||||
{
|
||||
pcre2_code *re;
|
||||
PCRE2_SPTR pattern; /* PCRE2_SPTR is a pointer to unsigned code units of */
|
||||
PCRE2_SPTR subject; /* the appropriate width (8, 16, or 32 bits). */
|
||||
PCRE2_SPTR name_table;
|
||||
|
||||
int crlf_is_newline;
|
||||
int errornumber;
|
||||
int find_all;
|
||||
int i;
|
||||
int namecount;
|
||||
int name_entry_size;
|
||||
int rc;
|
||||
int utf8;
|
||||
|
||||
uint32_t option_bits;
|
||||
uint32_t newline;
|
||||
|
||||
PCRE2_SIZE erroroffset;
|
||||
PCRE2_SIZE *ovector;
|
||||
|
||||
size_t subject_length;
|
||||
pcre2_match_data *match_data;
|
||||
|
||||
|
||||
|
||||
/**************************************************************************
|
||||
* First, sort out the command line. There is only one possible option at *
|
||||
* the moment, "-g" to request repeated matching to find all occurrences, *
|
||||
* like Perl's /g option. We set the variable find_all to a non-zero value *
|
||||
* if the -g option is present. Apart from that, there must be exactly two *
|
||||
* arguments. *
|
||||
**************************************************************************/
|
||||
|
||||
find_all = 0;
|
||||
for (i = 1; i < argc; i++)
|
||||
{
|
||||
if (strcmp(argv[i], "-g") == 0) find_all = 1;
|
||||
else break;
|
||||
}
|
||||
|
||||
/* After the options, we require exactly two arguments, which are the pattern,
|
||||
and the subject string. */
|
||||
|
||||
if (argc - i != 2)
|
||||
{
|
||||
printf("Two arguments required: a regex and a subject string\n");
|
||||
return 1;
|
||||
}
|
||||
|
||||
/* As pattern and subject are char arguments, they can be straightforwardly
|
||||
cast to PCRE2_SPTR as we are working in 8-bit code units. */
|
||||
|
||||
pattern = (PCRE2_SPTR)argv[i];
|
||||
subject = (PCRE2_SPTR)argv[i+1];
|
||||
subject_length = strlen((char *)subject);
|
||||
|
||||
|
||||
/*************************************************************************
|
||||
* Now we are going to compile the regular expression pattern, and handle *
|
||||
* any errors that are detected. *
|
||||
*************************************************************************/
|
||||
|
||||
re = pcre2_compile(
|
||||
pattern, /* the pattern */
|
||||
-1, /* indicates pattern is zero-terminated */
|
||||
0, /* default options */
|
||||
&errornumber, /* for error number */
|
||||
&erroroffset, /* for error offset */
|
||||
NULL); /* use default compile context */
|
||||
|
||||
/* Compilation failed: print the error message and exit. */
|
||||
|
||||
if (re == NULL)
|
||||
{
|
||||
PCRE2_UCHAR buffer[256];
|
||||
pcre2_get_error_message(errornumber, buffer, sizeof(buffer));
|
||||
printf("PCRE2 compilation failed at offset %d: %s\n", (int)erroroffset,
|
||||
buffer);
|
||||
return 1;
|
||||
}
|
||||
|
||||
|
||||
/*************************************************************************
|
||||
* If the compilation succeeded, we call PCRE again, in order to do a *
|
||||
* pattern match against the subject string. This does just ONE match. If *
|
||||
* further matching is needed, it will be done below. Before running the *
|
||||
* match we must set up a match_data block for holding the result. *
|
||||
*************************************************************************/
|
||||
|
||||
/* Using this function ensures that the block is exactly the right size for
|
||||
the number of capturing parentheses in the pattern. */
|
||||
|
||||
match_data = pcre2_match_data_create_from_pattern(re, NULL);
|
||||
|
||||
rc = pcre2_match(
|
||||
re, /* the compiled pattern */
|
||||
subject, /* the subject string */
|
||||
subject_length, /* the length of the subject */
|
||||
0, /* start at offset 0 in the subject */
|
||||
0, /* default options */
|
||||
match_data, /* block for storing the result */
|
||||
NULL); /* use default match context */
|
||||
|
||||
/* Matching failed: handle error cases */
|
||||
|
||||
if (rc < 0)
|
||||
{
|
||||
switch(rc)
|
||||
{
|
||||
case PCRE2_ERROR_NOMATCH: printf("No match\n"); break;
|
||||
/*
|
||||
Handle other special cases if you like
|
||||
*/
|
||||
default: printf("Matching error %d\n", rc); break;
|
||||
}
|
||||
pcre2_match_data_free(match_data); /* Release memory used for the match */
|
||||
pcre2_code_free(re); /* data and the compiled pattern. */
|
||||
return 1;
|
||||
}
|
||||
|
||||
/* Match succeded. Get a pointer to the output vector, where string offsets are
|
||||
stored. */
|
||||
|
||||
ovector = pcre2_get_ovector_pointer(match_data);
|
||||
printf("\nMatch succeeded at offset %d\n", (int)ovector[0]);
|
||||
|
||||
|
||||
/*************************************************************************
|
||||
* We have found the first match within the subject string. If the output *
|
||||
* vector wasn't big enough, say so. Then output any substrings that were *
|
||||
* captured. *
|
||||
*************************************************************************/
|
||||
|
||||
/* The output vector wasn't big enough. This should not happen, because we used
|
||||
pcre2_match_data_create_from_pattern() above. */
|
||||
|
||||
if (rc == 0)
|
||||
printf("ovector was not big enough for all the captured substrings\n");
|
||||
|
||||
/* Show substrings stored in the output vector by number. Obviously, in a real
|
||||
application you might want to do things other than print them. */
|
||||
|
||||
for (i = 0; i < rc; i++)
|
||||
{
|
||||
PCRE2_SPTR substring_start = subject + ovector[2*i];
|
||||
size_t substring_length = ovector[2*i+1] - ovector[2*i];
|
||||
printf("%2d: %.*s\n", i, (int)substring_length, (char *)substring_start);
|
||||
}
|
||||
|
||||
|
||||
/**************************************************************************
|
||||
* That concludes the basic part of this demonstration program. We have *
|
||||
* compiled a pattern, and performed a single match. The code that follows *
|
||||
* shows first how to access named substrings, and then how to code for *
|
||||
* repeated matches on the same subject. *
|
||||
**************************************************************************/
|
||||
|
||||
/* See if there are any named substrings, and if so, show them by name. First
|
||||
we have to extract the count of named parentheses from the pattern. */
|
||||
|
||||
(void)pcre2_pattern_info(
|
||||
re, /* the compiled pattern */
|
||||
PCRE2_INFO_NAMECOUNT, /* get the number of named substrings */
|
||||
&namecount); /* where to put the answer */
|
||||
|
||||
if (namecount <= 0) printf("No named substrings\n"); else
|
||||
{
|
||||
PCRE2_SPTR tabptr;
|
||||
printf("Named substrings\n");
|
||||
|
||||
/* Before we can access the substrings, we must extract the table for
|
||||
translating names to numbers, and the size of each entry in the table. */
|
||||
|
||||
(void)pcre2_pattern_info(
|
||||
re, /* the compiled pattern */
|
||||
PCRE2_INFO_NAMETABLE, /* address of the table */
|
||||
&name_table); /* where to put the answer */
|
||||
|
||||
(void)pcre2_pattern_info(
|
||||
re, /* the compiled pattern */
|
||||
PCRE2_INFO_NAMEENTRYSIZE, /* size of each entry in the table */
|
||||
&name_entry_size); /* where to put the answer */
|
||||
|
||||
/* Now we can scan the table and, for each entry, print the number, the name,
|
||||
and the substring itself. In the 8-bit library the number is held in two
|
||||
bytes, most significant first. */
|
||||
|
||||
tabptr = name_table;
|
||||
for (i = 0; i < namecount; i++)
|
||||
{
|
||||
int n = (tabptr[0] << 8) | tabptr[1];
|
||||
printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2,
|
||||
(int)(ovector[2*n+1] - ovector[2*n]), subject + ovector[2*n]);
|
||||
tabptr += name_entry_size;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/*************************************************************************
|
||||
* If the "-g" option was given on the command line, we want to continue *
|
||||
* to search for additional matches in the subject string, in a similar *
|
||||
* way to the /g option in Perl. This turns out to be trickier than you *
|
||||
* might think because of the possibility of matching an empty string. *
|
||||
* What happens is as follows: *
|
||||
* *
|
||||
* If the previous match was NOT for an empty string, we can just start *
|
||||
* the next match at the end of the previous one. *
|
||||
* *
|
||||
* If the previous match WAS for an empty string, we can't do that, as it *
|
||||
* would lead to an infinite loop. Instead, a call of pcre2_match() is *
|
||||
* made with the PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set. The *
|
||||
* first of these tells PCRE2 that an empty string at the start of the *
|
||||
* subject is not a valid match; other possibilities must be tried. The *
|
||||
* second flag restricts PCRE2 to one match attempt at the initial string *
|
||||
* position. If this match succeeds, an alternative to the empty string *
|
||||
* match has been found, and we can print it and proceed round the loop, *
|
||||
* advancing by the length of whatever was found. If this match does not *
|
||||
* succeed, we still stay in the loop, advancing by just one character. *
|
||||
* In UTF-8 mode, which can be set by (*UTF) in the pattern, this may be *
|
||||
* more than one byte. *
|
||||
* *
|
||||
* However, there is a complication concerned with newlines. When the *
|
||||
* newline convention is such that CRLF is a valid newline, we must *
|
||||
* advance by two characters rather than one. The newline convention can *
|
||||
* be set in the regex by (*CR), etc.; if not, we must find the default. *
|
||||
*************************************************************************/
|
||||
|
||||
if (!find_all) /* Check for -g */
|
||||
{
|
||||
pcre2_match_data_free(match_data); /* Release the memory that was used */
|
||||
pcre2_code_free(re); /* for the match data and the pattern. */
|
||||
return 0; /* Exit the program. */
|
||||
}
|
||||
|
||||
/* Before running the loop, check for UTF-8 and whether CRLF is a valid newline
|
||||
sequence. First, find the options with which the regex was compiled and extract
|
||||
the UTF state. */
|
||||
|
||||
(void)pcre2_pattern_info(re, PCRE2_INFO_ALLOPTIONS, &option_bits);
|
||||
utf8 = (option_bits & PCRE2_UTF) != 0;
|
||||
|
||||
/* Now find the newline convention and see whether CRLF is a valid newline
|
||||
sequence. */
|
||||
|
||||
(void)pcre2_pattern_info(re, PCRE2_INFO_NEWLINE, &newline);
|
||||
crlf_is_newline = newline == PCRE2_NEWLINE_ANY ||
|
||||
newline == PCRE2_NEWLINE_CRLF ||
|
||||
newline == PCRE2_NEWLINE_ANYCRLF;
|
||||
|
||||
/* Loop for second and subsequent matches */
|
||||
|
||||
for (;;)
|
||||
{
|
||||
uint32_t options = 0; /* Normally no options */
|
||||
PCRE2_SIZE start_offset = ovector[1]; /* Start at end of previous match */
|
||||
|
||||
/* If the previous match was for an empty string, we are finished if we are
|
||||
at the end of the subject. Otherwise, arrange to run another match at the
|
||||
same point to see if a non-empty match can be found. */
|
||||
|
||||
if (ovector[0] == ovector[1])
|
||||
{
|
||||
if (ovector[0] == subject_length) break;
|
||||
options = PCRE2_NOTEMPTY_ATSTART | PCRE2_ANCHORED;
|
||||
}
|
||||
|
||||
/* Run the next matching operation */
|
||||
|
||||
rc = pcre2_match(
|
||||
re, /* the compiled pattern */
|
||||
subject, /* the subject string */
|
||||
subject_length, /* the length of the subject */
|
||||
start_offset, /* starting offset in the subject */
|
||||
options, /* options */
|
||||
match_data, /* block for storing the result */
|
||||
NULL); /* use default match context */
|
||||
|
||||
/* This time, a result of NOMATCH isn't an error. If the value in "options"
|
||||
is zero, it just means we have found all possible matches, so the loop ends.
|
||||
Otherwise, it means we have failed to find a non-empty-string match at a
|
||||
point where there was a previous empty-string match. In this case, we do what
|
||||
Perl does: advance the matching position by one character, and continue. We
|
||||
do this by setting the "end of previous match" offset, because that is picked
|
||||
up at the top of the loop as the point at which to start again.
|
||||
|
||||
There are two complications: (a) When CRLF is a valid newline sequence, and
|
||||
the current position is just before it, advance by an extra byte. (b)
|
||||
Otherwise we must ensure that we skip an entire UTF character if we are in
|
||||
UTF mode. */
|
||||
|
||||
if (rc == PCRE2_ERROR_NOMATCH)
|
||||
{
|
||||
if (options == 0) break; /* All matches found */
|
||||
ovector[1] = start_offset + 1; /* Advance one code unit */
|
||||
if (crlf_is_newline && /* If CRLF is newline & */
|
||||
start_offset < subject_length - 1 && /* we are at CRLF, */
|
||||
subject[start_offset] == '\r' &&
|
||||
subject[start_offset + 1] == '\n')
|
||||
ovector[1] += 1; /* Advance by one more. */
|
||||
else if (utf8) /* Otherwise, ensure we */
|
||||
{ /* advance a whole UTF-8 */
|
||||
while (ovector[1] < subject_length) /* character. */
|
||||
{
|
||||
if ((subject[ovector[1]] & 0xc0) != 0x80) break;
|
||||
ovector[1] += 1;
|
||||
}
|
||||
}
|
||||
continue; /* Go round the loop again */
|
||||
}
|
||||
|
||||
/* Other matching errors are not recoverable. */
|
||||
|
||||
if (rc < 0)
|
||||
{
|
||||
printf("Matching error %d\n", rc);
|
||||
pcre2_match_data_free(match_data);
|
||||
pcre2_code_free(re);
|
||||
return 1;
|
||||
}
|
||||
|
||||
/* Match succeded */
|
||||
|
||||
printf("\nMatch succeeded again at offset %d\n", (int)ovector[0]);
|
||||
|
||||
/* The match succeeded, but the output vector wasn't big enough. This
|
||||
should not happen. */
|
||||
|
||||
if (rc == 0)
|
||||
printf("ovector was not big enough for all the captured substrings\n");
|
||||
|
||||
/* As before, show substrings stored in the output vector by number, and then
|
||||
also any named substrings. */
|
||||
|
||||
for (i = 0; i < rc; i++)
|
||||
{
|
||||
PCRE2_SPTR substring_start = subject + ovector[2*i];
|
||||
size_t substring_length = ovector[2*i+1] - ovector[2*i];
|
||||
printf("%2d: %.*s\n", i, (int)substring_length, (char *)substring_start);
|
||||
}
|
||||
|
||||
if (namecount <= 0) printf("No named substrings\n"); else
|
||||
{
|
||||
PCRE2_SPTR tabptr = name_table;
|
||||
printf("Named substrings\n");
|
||||
for (i = 0; i < namecount; i++)
|
||||
{
|
||||
int n = (tabptr[0] << 8) | tabptr[1];
|
||||
printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2,
|
||||
(int)(ovector[2*n+1] - ovector[2*n]), subject + ovector[2*n]);
|
||||
tabptr += name_entry_size;
|
||||
}
|
||||
}
|
||||
} /* End of loop to find second and subsequent matches */
|
||||
|
||||
printf("\n");
|
||||
pcre2_match_data_free(match_data);
|
||||
pcre2_code_free(re);
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* End of pcre2demo.c */
|
||||
<p>
|
||||
Return to the <a href="index.html">PCRE2 index page</a>.
|
||||
</p>
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,270 @@
|
|||
<html>
|
||||
<head>
|
||||
<title>pcre2unicode specification</title>
|
||||
</head>
|
||||
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
|
||||
<h1>pcre2unicode man page</h1>
|
||||
<p>
|
||||
Return to the <a href="index.html">PCRE2 index page</a>.
|
||||
</p>
|
||||
<p>
|
||||
This page is part of the PCRE2 HTML documentation. It was generated
|
||||
automatically from the original man page. If there is any nonsense in it,
|
||||
please consult the man page, in case the conversion went wrong.
|
||||
<br>
|
||||
<br><b>
|
||||
UNICODE AND UTF SUPPORT
|
||||
</b><br>
|
||||
<P>
|
||||
When PCRE2 is built with Unicode support, it acquires knowledge of Unicode
|
||||
character properties and can process text strings in UTF-8, UTF-16, or UTF-32
|
||||
format (depending on the code unit width). By default, PCRE2 assumes that one
|
||||
code unit is one character. To process a pattern as a UTF string, where a
|
||||
character may require more than one code unit, you must call
|
||||
<a href="pcre2_compile.html"><b>pcre2_compile()</b></a>
|
||||
with the PCRE2_UTF option flag, or the pattern must start with the sequence
|
||||
(*UTF). When either of these is the case, both the pattern and any subject
|
||||
strings that are matched against it are treated as UTF strings instead of
|
||||
strings of individual one-code-unit characters.
|
||||
</P>
|
||||
<P>
|
||||
If you build PCRE2 with Unicode support, the library will be bigger, but the
|
||||
additional run time overhead is limited to testing the PCRE2_UTF flag
|
||||
occasionally, so should not be very much.
|
||||
</P>
|
||||
<br><b>
|
||||
UNICODE PROPERTY SUPPORT
|
||||
</b><br>
|
||||
<P>
|
||||
When PCRE2 is built with Unicode support, the escape sequences \p{..},
|
||||
\P{..}, and \X can be used. The Unicode properties that can be tested are
|
||||
limited to the general category properties such as Lu for an upper case letter
|
||||
or Nd for a decimal number, the Unicode script names such as Arabic or Han, and
|
||||
the derived properties Any and L&. Full lists are given in the
|
||||
<a href="pcre2pattern.html"><b>pcre2pattern</b></a>
|
||||
and
|
||||
<a href="pcre2syntax.html"><b>pcre2syntax</b></a>
|
||||
documentation. Only the short names for properties are supported. For example,
|
||||
\p{L} matches a letter. Its Perl synonym, \p{Letter}, is not supported.
|
||||
Furthermore, in Perl, many properties may optionally be prefixed by "Is", for
|
||||
compatibility with Perl 5.6. PCRE does not support this.
|
||||
</P>
|
||||
<br><b>
|
||||
WIDE CHARACTERS AND UTF MODES
|
||||
</b><br>
|
||||
<P>
|
||||
Codepoints less than 256 can be specified in patterns by either braced or
|
||||
unbraced hexadecimal escape sequences (for example, \x{b3} or \xb3). Larger
|
||||
values have to use braced sequences. Unbraced octal code points up to \777 are
|
||||
also recognized; larger ones can be coded using \o{...}.
|
||||
</P>
|
||||
<P>
|
||||
In UTF modes, repeat quantifiers apply to complete UTF characters, not to
|
||||
individual code units.
|
||||
</P>
|
||||
<P>
|
||||
In UTF modes, the dot metacharacter matches one UTF character instead of a
|
||||
single code unit.
|
||||
</P>
|
||||
<P>
|
||||
The escape sequence \C can be used to match a single code unit, in a UTF mode,
|
||||
but its use can lead to some strange effects because it breaks up multi-unit
|
||||
characters (see the description of \C in the
|
||||
<a href="pcre2pattern.html"><b>pcre2pattern</b></a>
|
||||
documentation). The use of \C is not supported in the alternative matching
|
||||
function <b>pcre2_dfa_exec()</b>, nor is it supported in UTF mode by the JIT
|
||||
optimization. If JIT optimization is requested for a UTF pattern that contains
|
||||
\C, it will not succeed, and so the matching will be carried out by the normal
|
||||
interpretive function.
|
||||
</P>
|
||||
<P>
|
||||
The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly test
|
||||
characters of any code value, but, by default, the characters that PCRE2
|
||||
recognizes as digits, spaces, or word characters remain the same set as in
|
||||
non-UTF mode, all with code points less than 256. This remains true even when
|
||||
PCRE2 is built to include Unicode support, because to do otherwise would slow
|
||||
down matching in many common cases. Note that this also applies to \b
|
||||
and \B, because they are defined in terms of \w and \W. If you want
|
||||
to test for a wider sense of, say, "digit", you can use explicit Unicode
|
||||
property tests such as \p{Nd}. Alternatively, if you set the PCRE2_UCP option,
|
||||
the way that the character escapes work is changed so that Unicode properties
|
||||
are used to determine which characters match. There are more details in the
|
||||
section on
|
||||
<a href="pcre2pattern.html#genericchartypes">generic character types</a>
|
||||
in the
|
||||
<a href="pcre2pattern.html"><b>pcre2pattern</b></a>
|
||||
documentation.
|
||||
</P>
|
||||
<P>
|
||||
Similarly, characters that match the POSIX named character classes are all
|
||||
low-valued characters, unless the PCRE2_UCP option is set.
|
||||
</P>
|
||||
<P>
|
||||
However, the special horizontal and vertical white space matching escapes (\h,
|
||||
\H, \v, and \V) do match all the appropriate Unicode characters, whether or
|
||||
not PCRE2_UCP is set.
|
||||
</P>
|
||||
<P>
|
||||
Case-insensitive matching in UTF mode makes use of Unicode properties. A few
|
||||
Unicode characters such as Greek sigma have more than two codepoints that are
|
||||
case-equivalent, and these are treated as such.
|
||||
</P>
|
||||
<br><b>
|
||||
VALIDITY OF UTF STRINGS
|
||||
</b><br>
|
||||
<P>
|
||||
When the PCRE2_UTF option is set, the strings passed as patterns and subjects
|
||||
are (by default) checked for validity on entry to the relevant functions.
|
||||
If an invalid UTF string is passed, an error return is given.
|
||||
</P>
|
||||
<P>
|
||||
UTF-16 and UTF-32 strings can indicate their endianness by special code knows
|
||||
as a byte-order mark (BOM). The PCRE2 functions do not handle this, expecting
|
||||
strings to be in host byte order.
|
||||
</P>
|
||||
<P>
|
||||
The entire string is checked before any other processing takes place. In
|
||||
addition to checking the format of the string, there is a check to ensure that
|
||||
all code points lie in the range U+0 to U+10FFFF, excluding the surrogate area.
|
||||
The so-called "non-character" code points are not excluded because Unicode
|
||||
corrigendum #9 makes it clear that they should not be.
|
||||
</P>
|
||||
<P>
|
||||
Characters in the "Surrogate Area" of Unicode are reserved for use by UTF-16,
|
||||
where they are used in pairs to encode code points with values greater than
|
||||
0xFFFF. The code points that are encoded by UTF-16 pairs are available
|
||||
independently in the UTF-8 and UTF-32 encodings. (In other words, the whole
|
||||
surrogate thing is a fudge for UTF-16 which unfortunately messes up UTF-8 and
|
||||
UTF-32.)
|
||||
</P>
|
||||
<P>
|
||||
In some situations, you may already know that your strings are valid, and
|
||||
therefore want to skip these checks in order to improve performance, for
|
||||
example in the case of a long subject string that is being scanned repeatedly.
|
||||
If you set the PCRE2_NO_UTF_CHECK flag at compile time or at run time, PCRE2
|
||||
assumes that the pattern or subject it is given (respectively) contains only
|
||||
valid UTF code unit sequences.
|
||||
</P>
|
||||
<P>
|
||||
Passing PCRE2_NO_UTF_CHECK to <b>pcre2_compile()</b> just disables the check for
|
||||
the pattern; it does not also apply to subject strings. If you want to disable
|
||||
the check for a subject string you must pass this option to <b>pcre2_exec()</b>
|
||||
or <b>pcre2_dfa_exec()</b>.
|
||||
</P>
|
||||
<P>
|
||||
If you pass an invalid UTF string when PCRE2_NO_UTF_CHECK is set, the result
|
||||
is undefined and your program may crash or loop indefinitely.
|
||||
<a name="utf8strings"></a></P>
|
||||
<br><b>
|
||||
Errors in UTF-8 strings
|
||||
</b><br>
|
||||
<P>
|
||||
The following negative error codes are given for invalid UTF-8 strings:
|
||||
<pre>
|
||||
PCRE2_ERROR_UTF8_ERR1
|
||||
PCRE2_ERROR_UTF8_ERR2
|
||||
PCRE2_ERROR_UTF8_ERR3
|
||||
PCRE2_ERROR_UTF8_ERR4
|
||||
PCRE2_ERROR_UTF8_ERR5
|
||||
</pre>
|
||||
The string ends with a truncated UTF-8 character; the code specifies how many
|
||||
bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be
|
||||
no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279)
|
||||
allows for up to 6 bytes, and this is checked first; hence the possibility of
|
||||
4 or 5 missing bytes.
|
||||
<pre>
|
||||
PCRE2_ERROR_UTF8_ERR6
|
||||
PCRE2_ERROR_UTF8_ERR7
|
||||
PCRE2_ERROR_UTF8_ERR8
|
||||
PCRE2_ERROR_UTF8_ERR9
|
||||
PCRE2_ERROR_UTF8_ERR10
|
||||
</pre>
|
||||
The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the
|
||||
character do not have the binary value 0b10 (that is, either the most
|
||||
significant bit is 0, or the next bit is 1).
|
||||
<pre>
|
||||
PCRE2_ERROR_UTF8_ERR11
|
||||
PCRE2_ERROR_UTF8_ERR12
|
||||
</pre>
|
||||
A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long;
|
||||
these code points are excluded by RFC 3629.
|
||||
<pre>
|
||||
PCRE2_ERROR_UTF8_ERR13
|
||||
</pre>
|
||||
A 4-byte character has a value greater than 0x10fff; these code points are
|
||||
excluded by RFC 3629.
|
||||
<pre>
|
||||
PCRE2_ERROR_UTF8_ERR14
|
||||
</pre>
|
||||
A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of
|
||||
code points are reserved by RFC 3629 for use with UTF-16, and so are excluded
|
||||
from UTF-8.
|
||||
<pre>
|
||||
PCRE2_ERROR_UTF8_ERR15
|
||||
PCRE2_ERROR_UTF8_ERR16
|
||||
PCRE2_ERROR_UTF8_ERR17
|
||||
PCRE2_ERROR_UTF8_ERR18
|
||||
PCRE2_ERROR_UTF8_ERR19
|
||||
</pre>
|
||||
A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a
|
||||
value that can be represented by fewer bytes, which is invalid. For example,
|
||||
the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just
|
||||
one byte.
|
||||
<pre>
|
||||
PCRE2_ERROR_UTF8_ERR20
|
||||
</pre>
|
||||
The two most significant bits of the first byte of a character have the binary
|
||||
value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a
|
||||
byte can only validly occur as the second or subsequent byte of a multi-byte
|
||||
character.
|
||||
<pre>
|
||||
PCRE2_ERROR_UTF8_ERR21
|
||||
</pre>
|
||||
The first byte of a character has the value 0xfe or 0xff. These values can
|
||||
never occur in a valid UTF-8 string.
|
||||
<a name="utf16strings"></a></P>
|
||||
<br><b>
|
||||
Errors in UTF-16 strings
|
||||
</b><br>
|
||||
<P>
|
||||
The following negative error codes are given for invalid UTF-16 strings:
|
||||
<pre>
|
||||
PCRE_UTF16_ERR1 Missing low surrogate at end of string
|
||||
PCRE_UTF16_ERR2 Invalid low surrogate follows high surrogate
|
||||
PCRE_UTF16_ERR3 Isolated low surrogate
|
||||
|
||||
<a name="utf32strings"></a></PRE>
|
||||
</P>
|
||||
<br><b>
|
||||
Errors in UTF-32 strings
|
||||
</b><br>
|
||||
<P>
|
||||
The following negative error codes are given for invalid UTF-32 strings:
|
||||
<pre>
|
||||
PCRE_UTF32_ERR1 Surrogate character (range from 0xd800 to 0xdfff)
|
||||
PCRE_UTF32_ERR2 Code point is greater than 0x10ffff
|
||||
|
||||
</PRE>
|
||||
</P>
|
||||
<br><b>
|
||||
AUTHOR
|
||||
</b><br>
|
||||
<P>
|
||||
Philip Hazel
|
||||
<br>
|
||||
University Computing Service
|
||||
<br>
|
||||
Cambridge CB2 3QH, England.
|
||||
<br>
|
||||
</P>
|
||||
<br><b>
|
||||
REVISION
|
||||
</b><br>
|
||||
<P>
|
||||
Last updated: 16 September 2014
|
||||
<br>
|
||||
Copyright © 1997-2014 University of Cambridge.
|
||||
<br>
|
||||
<p>
|
||||
Return to the <a href="index.html">PCRE2 index page</a>.
|
||||
</p>
|
||||
|
|
@ -0,0 +1,177 @@
|
|||
<html>
|
||||
<!-- This is a manually maintained file that is the root of the HTML version of
|
||||
the PCRE2 documentation. When the HTML documents are built from the man
|
||||
page versions, the entire doc/html directory is emptied, this file is then
|
||||
copied into doc/html/index.html, and the remaining files therein are
|
||||
created by the 132html script.
|
||||
-->
|
||||
<head>
|
||||
<title>PCRE2 specification</title>
|
||||
</head>
|
||||
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
|
||||
<h1>Perl-compatible Regular Expressions (revised API: PCRE2)</h1>
|
||||
<p>
|
||||
The HTML documentation for PCRE2 consists of a number of pages that are listed
|
||||
below in alphabetical order. If you are new to PCRE2, please read the first one
|
||||
first.
|
||||
</p>
|
||||
|
||||
<table>
|
||||
<tr><td><a href="pcre2.html">pcre</a></td>
|
||||
<td> Introductory page</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2-config.html">pcre-config</a></td>
|
||||
<td> Information about the installation configuration</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2api.html">pcreapi</a></td>
|
||||
<td> PCRE2's native API</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2build.html">pcrebuild</a></td>
|
||||
<td> Building PCRE2</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2callout.html">pcre2callout</a></td>
|
||||
<td> The <i>callout</i> facility</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2compat.html">pcre2compat</a></td>
|
||||
<td> Compability with Perl</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2demo.html">pcre2demo</a></td>
|
||||
<td> A demonstration C program that uses the PCRE2 library</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2grep.html">pcre2grep</a></td>
|
||||
<td> The <b>pcre2grep</b> command</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2jit.html">pcre2jit</a></td>
|
||||
<td> Discussion of the just-in-time optimization support</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2limits.html">pcre2limits</a></td>
|
||||
<td> Details of size and other limits</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2matching.html">pcre2matching</a></td>
|
||||
<td> Discussion of the two matching algorithms</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2partial.html">pcre2partial</a></td>
|
||||
<td> Using PCRE2 for partial matching</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2pattern.html">pcre2pattern</a></td>
|
||||
<td> Specification of the regular expressions supported by PCRE2</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2perform.html">pcre2perform</a></td>
|
||||
<td> Some comments on performance</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2posix.html">pcre2posix</a></td>
|
||||
<td> The POSIX API to the PCRE2 8-bit library</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2precompile.html">pcre2precompile</a></td>
|
||||
<td> How to save and re-use compiled patterns</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2sample.html">pcre2sample</a></td>
|
||||
<td> Discussion of the pcre2demo program</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2stack.html">pcre2stack</a></td>
|
||||
<td> Discussion of PCRE2's stack usage</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2syntax.html">pcre2syntax</a></td>
|
||||
<td> Syntax quick-reference summary</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2test.html">pcre2test</a></td>
|
||||
<td> The <b>pcre2test</b> command for testing PCRE2</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2unicode.html">pcre2unicode</a></td>
|
||||
<td> Discussion of Unicode and UTF-8/UTF-16/UTF-32 support</td></tr>
|
||||
</table>
|
||||
|
||||
<p>
|
||||
There are also individual pages that summarize the interface for each function
|
||||
in the library. There is a single page for each triple of 8-bit/16-bit/32-bit
|
||||
functions.
|
||||
</p>
|
||||
|
||||
<table>
|
||||
|
||||
<tr><td><a href="pcre2_assign_jit_stack.html">pcre2_assign_jit_stack</a></td>
|
||||
<td> Assign stack for JIT matching</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_compile.html">pcre2_compile</a></td>
|
||||
<td> Compile a regular expression</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_compile2.html">pcre2_compile2</a></td>
|
||||
<td> Compile a regular expression (alternate interface)</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_config.html">pcre2_config</a></td>
|
||||
<td> Show build-time configuration options</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_copy_named_substring.html">pcre2_copy_named_substring</a></td>
|
||||
<td> Extract named substring into given buffer</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_copy_substring.html">pcre2_copy_substring</a></td>
|
||||
<td> Extract numbered substring into given buffer</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_dfa_exec.html">pcre2_dfa_exec</a></td>
|
||||
<td> Match a compiled pattern to a subject string
|
||||
(DFA algorithm; <i>not</i> Perl compatible)</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_exec.html">pcre2_exec</a></td>
|
||||
<td> Match a compiled pattern to a subject string
|
||||
(Perl compatible)</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_free_study.html">pcre2_free_study</a></td>
|
||||
<td> Free study data</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_free_substring.html">pcre2_free_substring</a></td>
|
||||
<td> Free extracted substring</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_free_substring_list.html">pcre2_free_substring_list</a></td>
|
||||
<td> Free list of extracted substrings</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_fullinfo.html">pcre2_fullinfo</a></td>
|
||||
<td> Extract information about a pattern</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_get_named_substring.html">pcre2_get_named_substring</a></td>
|
||||
<td> Extract named substring into new memory</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_get_stringnumber.html">pcre2_get_stringnumber</a></td>
|
||||
<td> Convert captured string name to number</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_get_stringtable_entries.html">pcre2_get_stringtable_entries</a></td>
|
||||
<td> Find table entries for given string name</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_get_substring.html">pcre2_get_substring</a></td>
|
||||
<td> Extract numbered substring into new memory</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_get_substring_list.html">pcre2_get_substring_list</a></td>
|
||||
<td> Extract all substrings into new memory</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_jit_exec.html">pcre2_jit_exec</a></td>
|
||||
<td> Fast path interface to JIT matching</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_jit_stack_alloc.html">pcre2_jit_stack_alloc</a></td>
|
||||
<td> Create a stack for JIT matching</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_jit_stack_free.html">pcre2_jit_stack_free</a></td>
|
||||
<td> Free a JIT matching stack</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_maketables.html">pcre2_maketables</a></td>
|
||||
<td> Build character tables in current locale</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_pattern_to_host_byte_order.html">pcre2_pattern_to_host_byte_order</a></td>
|
||||
<td> Convert compiled pattern to host byte order if necessary</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_refcount.html">pcre2_refcount</a></td>
|
||||
<td> Maintain reference count in compiled pattern</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_study.html">pcre2_study</a></td>
|
||||
<td> Study a compiled pattern</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_utf16_to_host_byte_order.html">pcre2_utf16_to_host_byte_order</a></td>
|
||||
<td> Convert UTF-16 string to host byte order if necessary</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_utf32_to_host_byte_order.html">pcre2_utf32_to_host_byte_order</a></td>
|
||||
<td> Convert UTF-32 string to host byte order if necessary</td></tr>
|
||||
|
||||
<tr><td><a href="pcre2_version.html">pcre2_version</a></td>
|
||||
<td> Return PCRE2 version and release date</td></tr>
|
||||
</table>
|
||||
|
||||
</html>
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -214,7 +214,7 @@ document for an overview of all the PCRE2 documentation.
|
|||
.B int pcre2_pattern_info(const pcre2 *\fIcode\fP, uint32_t \fIwhat\fP, void *\fIwhere\fP);
|
||||
.sp
|
||||
.B int pcre2_config(uint32_t \fIwhat\fP, void *\fIwhere\fP, PCRE2_SIZE \fIlength\fP);
|
||||
.sp
|
||||
.fi
|
||||
.
|
||||
.
|
||||
.SH "PCRE2 8-BIT, 16-BIT, AND 32-BIT LIBRARIES"
|
||||
|
|
|
|||
|
|
@ -0,0 +1,441 @@
|
|||
.\" Start example.
|
||||
.de EX
|
||||
. nr mE \\n(.f
|
||||
. nf
|
||||
. nh
|
||||
. ft CW
|
||||
..
|
||||
.
|
||||
.
|
||||
.\" End example.
|
||||
.de EE
|
||||
. ft \\n(mE
|
||||
. fi
|
||||
. hy \\n(HY
|
||||
..
|
||||
.
|
||||
.EX
|
||||
/*************************************************
|
||||
* PCRE2 DEMONSTRATION PROGRAM *
|
||||
*************************************************/
|
||||
|
||||
/* This is a demonstration program to illustrate a straightforward way of
|
||||
calling the PCRE2 regular expression library from a C program. See the
|
||||
pcre2sample documentation for a short discussion ("man pcre2sample" if you have
|
||||
the PCRE2 man pages installed). PCRE2 is a revised API for the library, and is
|
||||
incompatible with the original PCRE API.
|
||||
|
||||
There are actually three libraries, each supporting a different code unit
|
||||
width. This demonstration program uses the 8-bit library.
|
||||
|
||||
In Unix-like environments, if PCRE2 is installed in your standard system
|
||||
libraries, you should be able to compile this program using this command:
|
||||
|
||||
gcc -Wall pcre2demo.c -lpcre2-8 -o pcre2demo
|
||||
|
||||
If PCRE2 is not installed in a standard place, it is likely to be installed
|
||||
with support for the pkg-config mechanism. If you have pkg-config, you can
|
||||
compile this program using this command:
|
||||
|
||||
gcc -Wall pcre2demo.c `pkg-config --cflags --libs libpcre2-8` -o pcre2demo
|
||||
|
||||
If you do not have pkg-config, you may have to use this:
|
||||
|
||||
gcc -Wall pcre2demo.c -I/usr/local/include -L/usr/local/lib \e
|
||||
-R/usr/local/lib -lpcre2-8 -o pcre2demo
|
||||
|
||||
Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and
|
||||
library files for PCRE2 are installed on your system. Only some operating
|
||||
systems (Solaris is one) use the -R option.
|
||||
|
||||
Building under Windows:
|
||||
|
||||
If you want to statically link this program against a non-dll .a file, you must
|
||||
define PCRE2_STATIC before including pcre2.h, so in this environment, uncomment
|
||||
the following line. */
|
||||
|
||||
/* #define PCRE2_STATIC */
|
||||
|
||||
/* This macro must be defined before including pcre2.h. For a program that uses
|
||||
only one code unit width, it makes it possible to use generic function names
|
||||
such as pcre2_compile(). */
|
||||
|
||||
#define PCRE2_CODE_UNIT_WIDTH 8
|
||||
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
#include <pcre2.h>
|
||||
|
||||
|
||||
/**************************************************************************
|
||||
* Here is the program. The API includes the concept of "contexts" for *
|
||||
* setting up unusual interface requirements for compiling and matching, *
|
||||
* such as custom memory managers and non-standard newline definitions. *
|
||||
* This program does not do any of this, so it makes no use of contexts, *
|
||||
* always passing NULL where a context could be given. *
|
||||
**************************************************************************/
|
||||
|
||||
int main(int argc, char **argv)
|
||||
{
|
||||
pcre2_code *re;
|
||||
PCRE2_SPTR pattern; /* PCRE2_SPTR is a pointer to unsigned code units of */
|
||||
PCRE2_SPTR subject; /* the appropriate width (8, 16, or 32 bits). */
|
||||
PCRE2_SPTR name_table;
|
||||
|
||||
int crlf_is_newline;
|
||||
int errornumber;
|
||||
int find_all;
|
||||
int i;
|
||||
int namecount;
|
||||
int name_entry_size;
|
||||
int rc;
|
||||
int utf8;
|
||||
|
||||
uint32_t option_bits;
|
||||
uint32_t newline;
|
||||
|
||||
PCRE2_SIZE erroroffset;
|
||||
PCRE2_SIZE *ovector;
|
||||
|
||||
size_t subject_length;
|
||||
pcre2_match_data *match_data;
|
||||
|
||||
|
||||
|
||||
/**************************************************************************
|
||||
* First, sort out the command line. There is only one possible option at *
|
||||
* the moment, "-g" to request repeated matching to find all occurrences, *
|
||||
* like Perl's /g option. We set the variable find_all to a non-zero value *
|
||||
* if the -g option is present. Apart from that, there must be exactly two *
|
||||
* arguments. *
|
||||
**************************************************************************/
|
||||
|
||||
find_all = 0;
|
||||
for (i = 1; i < argc; i++)
|
||||
{
|
||||
if (strcmp(argv[i], "-g") == 0) find_all = 1;
|
||||
else break;
|
||||
}
|
||||
|
||||
/* After the options, we require exactly two arguments, which are the pattern,
|
||||
and the subject string. */
|
||||
|
||||
if (argc - i != 2)
|
||||
{
|
||||
printf("Two arguments required: a regex and a subject string\en");
|
||||
return 1;
|
||||
}
|
||||
|
||||
/* As pattern and subject are char arguments, they can be straightforwardly
|
||||
cast to PCRE2_SPTR as we are working in 8-bit code units. */
|
||||
|
||||
pattern = (PCRE2_SPTR)argv[i];
|
||||
subject = (PCRE2_SPTR)argv[i+1];
|
||||
subject_length = strlen((char *)subject);
|
||||
|
||||
|
||||
/*************************************************************************
|
||||
* Now we are going to compile the regular expression pattern, and handle *
|
||||
* any errors that are detected. *
|
||||
*************************************************************************/
|
||||
|
||||
re = pcre2_compile(
|
||||
pattern, /* the pattern */
|
||||
-1, /* indicates pattern is zero-terminated */
|
||||
0, /* default options */
|
||||
&errornumber, /* for error number */
|
||||
&erroroffset, /* for error offset */
|
||||
NULL); /* use default compile context */
|
||||
|
||||
/* Compilation failed: print the error message and exit. */
|
||||
|
||||
if (re == NULL)
|
||||
{
|
||||
PCRE2_UCHAR buffer[256];
|
||||
pcre2_get_error_message(errornumber, buffer, sizeof(buffer));
|
||||
printf("PCRE2 compilation failed at offset %d: %s\en", (int)erroroffset,
|
||||
buffer);
|
||||
return 1;
|
||||
}
|
||||
|
||||
|
||||
/*************************************************************************
|
||||
* If the compilation succeeded, we call PCRE again, in order to do a *
|
||||
* pattern match against the subject string. This does just ONE match. If *
|
||||
* further matching is needed, it will be done below. Before running the *
|
||||
* match we must set up a match_data block for holding the result. *
|
||||
*************************************************************************/
|
||||
|
||||
/* Using this function ensures that the block is exactly the right size for
|
||||
the number of capturing parentheses in the pattern. */
|
||||
|
||||
match_data = pcre2_match_data_create_from_pattern(re, NULL);
|
||||
|
||||
rc = pcre2_match(
|
||||
re, /* the compiled pattern */
|
||||
subject, /* the subject string */
|
||||
subject_length, /* the length of the subject */
|
||||
0, /* start at offset 0 in the subject */
|
||||
0, /* default options */
|
||||
match_data, /* block for storing the result */
|
||||
NULL); /* use default match context */
|
||||
|
||||
/* Matching failed: handle error cases */
|
||||
|
||||
if (rc < 0)
|
||||
{
|
||||
switch(rc)
|
||||
{
|
||||
case PCRE2_ERROR_NOMATCH: printf("No match\en"); break;
|
||||
/*
|
||||
Handle other special cases if you like
|
||||
*/
|
||||
default: printf("Matching error %d\en", rc); break;
|
||||
}
|
||||
pcre2_match_data_free(match_data); /* Release memory used for the match */
|
||||
pcre2_code_free(re); /* data and the compiled pattern. */
|
||||
return 1;
|
||||
}
|
||||
|
||||
/* Match succeded. Get a pointer to the output vector, where string offsets are
|
||||
stored. */
|
||||
|
||||
ovector = pcre2_get_ovector_pointer(match_data);
|
||||
printf("\enMatch succeeded at offset %d\en", (int)ovector[0]);
|
||||
|
||||
|
||||
/*************************************************************************
|
||||
* We have found the first match within the subject string. If the output *
|
||||
* vector wasn't big enough, say so. Then output any substrings that were *
|
||||
* captured. *
|
||||
*************************************************************************/
|
||||
|
||||
/* The output vector wasn't big enough. This should not happen, because we used
|
||||
pcre2_match_data_create_from_pattern() above. */
|
||||
|
||||
if (rc == 0)
|
||||
printf("ovector was not big enough for all the captured substrings\en");
|
||||
|
||||
/* Show substrings stored in the output vector by number. Obviously, in a real
|
||||
application you might want to do things other than print them. */
|
||||
|
||||
for (i = 0; i < rc; i++)
|
||||
{
|
||||
PCRE2_SPTR substring_start = subject + ovector[2*i];
|
||||
size_t substring_length = ovector[2*i+1] - ovector[2*i];
|
||||
printf("%2d: %.*s\en", i, (int)substring_length, (char *)substring_start);
|
||||
}
|
||||
|
||||
|
||||
/**************************************************************************
|
||||
* That concludes the basic part of this demonstration program. We have *
|
||||
* compiled a pattern, and performed a single match. The code that follows *
|
||||
* shows first how to access named substrings, and then how to code for *
|
||||
* repeated matches on the same subject. *
|
||||
**************************************************************************/
|
||||
|
||||
/* See if there are any named substrings, and if so, show them by name. First
|
||||
we have to extract the count of named parentheses from the pattern. */
|
||||
|
||||
(void)pcre2_pattern_info(
|
||||
re, /* the compiled pattern */
|
||||
PCRE2_INFO_NAMECOUNT, /* get the number of named substrings */
|
||||
&namecount); /* where to put the answer */
|
||||
|
||||
if (namecount <= 0) printf("No named substrings\en"); else
|
||||
{
|
||||
PCRE2_SPTR tabptr;
|
||||
printf("Named substrings\en");
|
||||
|
||||
/* Before we can access the substrings, we must extract the table for
|
||||
translating names to numbers, and the size of each entry in the table. */
|
||||
|
||||
(void)pcre2_pattern_info(
|
||||
re, /* the compiled pattern */
|
||||
PCRE2_INFO_NAMETABLE, /* address of the table */
|
||||
&name_table); /* where to put the answer */
|
||||
|
||||
(void)pcre2_pattern_info(
|
||||
re, /* the compiled pattern */
|
||||
PCRE2_INFO_NAMEENTRYSIZE, /* size of each entry in the table */
|
||||
&name_entry_size); /* where to put the answer */
|
||||
|
||||
/* Now we can scan the table and, for each entry, print the number, the name,
|
||||
and the substring itself. In the 8-bit library the number is held in two
|
||||
bytes, most significant first. */
|
||||
|
||||
tabptr = name_table;
|
||||
for (i = 0; i < namecount; i++)
|
||||
{
|
||||
int n = (tabptr[0] << 8) | tabptr[1];
|
||||
printf("(%d) %*s: %.*s\en", n, name_entry_size - 3, tabptr + 2,
|
||||
(int)(ovector[2*n+1] - ovector[2*n]), subject + ovector[2*n]);
|
||||
tabptr += name_entry_size;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/*************************************************************************
|
||||
* If the "-g" option was given on the command line, we want to continue *
|
||||
* to search for additional matches in the subject string, in a similar *
|
||||
* way to the /g option in Perl. This turns out to be trickier than you *
|
||||
* might think because of the possibility of matching an empty string. *
|
||||
* What happens is as follows: *
|
||||
* *
|
||||
* If the previous match was NOT for an empty string, we can just start *
|
||||
* the next match at the end of the previous one. *
|
||||
* *
|
||||
* If the previous match WAS for an empty string, we can't do that, as it *
|
||||
* would lead to an infinite loop. Instead, a call of pcre2_match() is *
|
||||
* made with the PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set. The *
|
||||
* first of these tells PCRE2 that an empty string at the start of the *
|
||||
* subject is not a valid match; other possibilities must be tried. The *
|
||||
* second flag restricts PCRE2 to one match attempt at the initial string *
|
||||
* position. If this match succeeds, an alternative to the empty string *
|
||||
* match has been found, and we can print it and proceed round the loop, *
|
||||
* advancing by the length of whatever was found. If this match does not *
|
||||
* succeed, we still stay in the loop, advancing by just one character. *
|
||||
* In UTF-8 mode, which can be set by (*UTF) in the pattern, this may be *
|
||||
* more than one byte. *
|
||||
* *
|
||||
* However, there is a complication concerned with newlines. When the *
|
||||
* newline convention is such that CRLF is a valid newline, we must *
|
||||
* advance by two characters rather than one. The newline convention can *
|
||||
* be set in the regex by (*CR), etc.; if not, we must find the default. *
|
||||
*************************************************************************/
|
||||
|
||||
if (!find_all) /* Check for -g */
|
||||
{
|
||||
pcre2_match_data_free(match_data); /* Release the memory that was used */
|
||||
pcre2_code_free(re); /* for the match data and the pattern. */
|
||||
return 0; /* Exit the program. */
|
||||
}
|
||||
|
||||
/* Before running the loop, check for UTF-8 and whether CRLF is a valid newline
|
||||
sequence. First, find the options with which the regex was compiled and extract
|
||||
the UTF state. */
|
||||
|
||||
(void)pcre2_pattern_info(re, PCRE2_INFO_ALLOPTIONS, &option_bits);
|
||||
utf8 = (option_bits & PCRE2_UTF) != 0;
|
||||
|
||||
/* Now find the newline convention and see whether CRLF is a valid newline
|
||||
sequence. */
|
||||
|
||||
(void)pcre2_pattern_info(re, PCRE2_INFO_NEWLINE, &newline);
|
||||
crlf_is_newline = newline == PCRE2_NEWLINE_ANY ||
|
||||
newline == PCRE2_NEWLINE_CRLF ||
|
||||
newline == PCRE2_NEWLINE_ANYCRLF;
|
||||
|
||||
/* Loop for second and subsequent matches */
|
||||
|
||||
for (;;)
|
||||
{
|
||||
uint32_t options = 0; /* Normally no options */
|
||||
PCRE2_SIZE start_offset = ovector[1]; /* Start at end of previous match */
|
||||
|
||||
/* If the previous match was for an empty string, we are finished if we are
|
||||
at the end of the subject. Otherwise, arrange to run another match at the
|
||||
same point to see if a non-empty match can be found. */
|
||||
|
||||
if (ovector[0] == ovector[1])
|
||||
{
|
||||
if (ovector[0] == subject_length) break;
|
||||
options = PCRE2_NOTEMPTY_ATSTART | PCRE2_ANCHORED;
|
||||
}
|
||||
|
||||
/* Run the next matching operation */
|
||||
|
||||
rc = pcre2_match(
|
||||
re, /* the compiled pattern */
|
||||
subject, /* the subject string */
|
||||
subject_length, /* the length of the subject */
|
||||
start_offset, /* starting offset in the subject */
|
||||
options, /* options */
|
||||
match_data, /* block for storing the result */
|
||||
NULL); /* use default match context */
|
||||
|
||||
/* This time, a result of NOMATCH isn't an error. If the value in "options"
|
||||
is zero, it just means we have found all possible matches, so the loop ends.
|
||||
Otherwise, it means we have failed to find a non-empty-string match at a
|
||||
point where there was a previous empty-string match. In this case, we do what
|
||||
Perl does: advance the matching position by one character, and continue. We
|
||||
do this by setting the "end of previous match" offset, because that is picked
|
||||
up at the top of the loop as the point at which to start again.
|
||||
|
||||
There are two complications: (a) When CRLF is a valid newline sequence, and
|
||||
the current position is just before it, advance by an extra byte. (b)
|
||||
Otherwise we must ensure that we skip an entire UTF character if we are in
|
||||
UTF mode. */
|
||||
|
||||
if (rc == PCRE2_ERROR_NOMATCH)
|
||||
{
|
||||
if (options == 0) break; /* All matches found */
|
||||
ovector[1] = start_offset + 1; /* Advance one code unit */
|
||||
if (crlf_is_newline && /* If CRLF is newline & */
|
||||
start_offset < subject_length - 1 && /* we are at CRLF, */
|
||||
subject[start_offset] == '\er' &&
|
||||
subject[start_offset + 1] == '\en')
|
||||
ovector[1] += 1; /* Advance by one more. */
|
||||
else if (utf8) /* Otherwise, ensure we */
|
||||
{ /* advance a whole UTF-8 */
|
||||
while (ovector[1] < subject_length) /* character. */
|
||||
{
|
||||
if ((subject[ovector[1]] & 0xc0) != 0x80) break;
|
||||
ovector[1] += 1;
|
||||
}
|
||||
}
|
||||
continue; /* Go round the loop again */
|
||||
}
|
||||
|
||||
/* Other matching errors are not recoverable. */
|
||||
|
||||
if (rc < 0)
|
||||
{
|
||||
printf("Matching error %d\en", rc);
|
||||
pcre2_match_data_free(match_data);
|
||||
pcre2_code_free(re);
|
||||
return 1;
|
||||
}
|
||||
|
||||
/* Match succeded */
|
||||
|
||||
printf("\enMatch succeeded again at offset %d\en", (int)ovector[0]);
|
||||
|
||||
/* The match succeeded, but the output vector wasn't big enough. This
|
||||
should not happen. */
|
||||
|
||||
if (rc == 0)
|
||||
printf("ovector was not big enough for all the captured substrings\en");
|
||||
|
||||
/* As before, show substrings stored in the output vector by number, and then
|
||||
also any named substrings. */
|
||||
|
||||
for (i = 0; i < rc; i++)
|
||||
{
|
||||
PCRE2_SPTR substring_start = subject + ovector[2*i];
|
||||
size_t substring_length = ovector[2*i+1] - ovector[2*i];
|
||||
printf("%2d: %.*s\en", i, (int)substring_length, (char *)substring_start);
|
||||
}
|
||||
|
||||
if (namecount <= 0) printf("No named substrings\en"); else
|
||||
{
|
||||
PCRE2_SPTR tabptr = name_table;
|
||||
printf("Named substrings\en");
|
||||
for (i = 0; i < namecount; i++)
|
||||
{
|
||||
int n = (tabptr[0] << 8) | tabptr[1];
|
||||
printf("(%d) %*s: %.*s\en", n, name_entry_size - 3, tabptr + 2,
|
||||
(int)(ovector[2*n+1] - ovector[2*n]), subject + ovector[2*n]);
|
||||
tabptr += name_entry_size;
|
||||
}
|
||||
}
|
||||
} /* End of loop to find second and subsequent matches */
|
||||
|
||||
printf("\en");
|
||||
pcre2_match_data_free(match_data);
|
||||
pcre2_code_free(re);
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* End of pcre2demo.c */
|
||||
.EE
|
||||
|
|
@ -366,7 +366,7 @@ include a closing square bracket in the characters, code it as \ex5D.
|
|||
A backslash followed by an equals sign marke the end of the subject string and
|
||||
the start of a modifier list. For example:
|
||||
.sp
|
||||
abc\=notbol,notempty
|
||||
abc\e=notbol,notempty
|
||||
.sp
|
||||
A backslash followed by any other non-alphanumeric character just escapes that
|
||||
character. A backslash followed by anything else causes an error. However, if
|
||||
|
|
@ -746,7 +746,7 @@ the actual match are indicated in the output by '<' or '>' characters
|
|||
underneath them. Here is an example:
|
||||
.sp
|
||||
/(?<=pqr)abc(?=xyz)/
|
||||
123pqrabcxyz456\=allusedtext
|
||||
123pqrabcxyz456\e=allusedtext
|
||||
0: pqrabcxyz
|
||||
<<< >>>
|
||||
.sp
|
||||
|
|
@ -789,7 +789,7 @@ The \fBcopy\fP and \fBget\fP modifiers can be used to test the
|
|||
They can be given more than once, and each can specify a group name or number,
|
||||
for example:
|
||||
.sp
|
||||
abcd\=copy=1,copy=3,get=G1
|
||||
abcd\e=copy=1,copy=3,get=G1
|
||||
.sp
|
||||
If the \fB#subject\fP command is used to set default copy and get lists, these
|
||||
can be unset by specifying a negative number for numbered groups and an empty
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load Diff
|
|
@ -420,4 +420,4 @@ pcre2_code_free(re);
|
|||
return 0;
|
||||
}
|
||||
|
||||
/* End of pcredemo.c */
|
||||
/* End of pcre2demo.c */
|
||||
|
|
|
|||
Loading…
Reference in New Issue