#! /bin/bash

# Script to prepare the files for building a PCRE2 release. It does some
# processing of the documentation and detrails files.

# 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:

# 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.

# LintMan     A Perl script that lints man pages looking for inconsistencies.

# AsciidocRender
#             A script that renders an AsciiDoc source as a manpage and HTML.

# 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.

# Set the LANG to C, because nroff converts ASCII "HYPHEN-MINUS" to Unicode
# "HYPHEN" if the system is using a UTF-8 locale (like "C.UTF-8").
export LANG=C LC_ALL=C

# Extract the current release version from configure.ac.
CURRENT_RELEASE=`grep -E 'm4_define\(pcre2_(major|minor|prerelease)' configure.ac | \
    grep -E -o '\[.*\]' | \
    sed -E -e '1s/$/./' | \
    tr -d '[]\n'`
export CURRENT_RELEASE

# First, sort out the documentation. The AsciiDoc sources are canonical; the
# retained troff files are used only to review the conversion.

cd doc
echo Processing documentation

# Generate pcre2demo.adoc directly from its C source.

echo "Making pcre2demo.adoc"
perl <<"END" >pcre2demo.adoc
  open(IN, "<", "../src/pcre2demo.c") or die "Failed to open src/pcre2demo.c";
  my $date = `git log -n1 --date=format:'%d %B %Y' --format=%cd ../src/pcre2demo.c`;
  chomp $date;
  my $version = $ENV{CURRENT_RELEASE};
  print "= pcre2demo(3)\n" .
        ":doctype: manpage\n" .
        ":manname: pcre2demo\n" .
        ":manpurpose: a demonstration C program for PCRE2\n" .
        ":manvolnum: 3\n" .
        ":manmanual: PCRE2\n" .
        ":mansource: PCRE2 $version\n" .
        ":docdate: $date\n" .
        ":revdate: $date\n\n" .
        "== Source Code\n\n" .
        "[source,role=wide]\n----\n";
  while (<IN>) { print; }
  print "----\n";
  close(IN);
END
if [ $? != 0 ] ; then exit 1; fi

# Verify the version number in AsciiDoc manpages and render them before their
# generated manpages are needed by the text and warning checks below.

for file in *.adoc ; do
  if ! grep -qE "^:mansource: PCRE2 $CURRENT_RELEASE$" "$file" ; then
    echo "Version number in $file does not match current release"
    exit 1
  fi
done

echo "Making HTML documentation"
find html -mindepth 1 -maxdepth 1 ! -name index.html -delete
cp ../README html/README.txt
cp ../NON-AUTOTOOLS-BUILD html/NON-AUTOTOOLS-BUILD.txt

mkdir -p man
/bin/rm -f man/*
for file in *.adoc ; do
  base=`basename $file .adoc`
  section=`sed -n 's/^:manvolnum: //p' "$file"`
  if [ "$section" != "1" ] && [ "$section" != "3" ] ; then
    echo "Invalid manpage section in $file"
    exit 1
  fi
  echo "  Making $base.$section and $base.html"
  ../maint/AsciidocRender "$file" "man/$base.$section" "html/$base.html"
  if [ $? != 0 ] ; then exit 1; fi
done

# 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 pcre2 pcre2api pcre2build pcre2callout pcre2compat pcre2jit \
            pcre2limits pcre2matching pcre2partial pcre2pattern pcre2perform \
            pcre2posix pcre2sample pcre2serialize pcre2syntax \
            pcre2unicode ; do
  echo "  Processing $file.3"
  nroff -c -man man/$file.3 >$file.rawtxt
  perl ../maint/CleanTxt <$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 pcre2grep pcre2-config ; do
  echo Making $file.txt
  nroff -c -man man/$file.1 >$file.rawtxt
  perl ../maint/CleanTxt <$file.rawtxt >$file.txt
  /bin/rm $file.rawtxt
done


# Verify that `man` can process the pages without warnings.
echo "Validating man pages"
if man --help 2>/dev/null | grep -q warnings ; then
  for file in man/*.1 man/*.3 ; do
    MAN_OUT=`MANROFFSEQ='' MANWIDTH=80 man --warnings=w,all -E UTF-8 -l -Tutf8 -Z "$file" 2>&1 >/dev/null`
    if [ "$MAN_OUT" != "" ]; then
      printf "Running man generated warnings:\n%s\n" "$MAN_OUT"
      exit 1
    fi
  done
elif [ -n "$CI" ] && [ -n "$GITHUB_REPOSITORY" ] ; then
  echo "::error title=UpdateAlways::man-db not installed in worker image"
else
  echo "Warning: skipping man-db warnings checking"
fi


# End of documentation processing; stop if only documentation required.

cd ..
echo Documentation done
if [ "$1" = "doc" ] ; then exit; fi

# These files are detrailed; do not detrail the test data because there may be
# significant trailing spaces. The configure files are also omitted from the
# detrailing.

txt_files=(
  AUTHORS.md
  BUILD.bazel
  CMakeLists.txt
  COPYING
  ChangeLog
  HACKING
  INSTALL
  LICENCE.md
  MODULE.bazel
  Makefile.am
  NEWS
  NON-AUTOTOOLS-BUILD
  README
  RunGrepTest
  RunGrepTest.py
  RunTest
  RunTest.py
  SECURITY.md
  SUPPORT-LIFECYCLE.md
  build.zig
  build.zig.zon
  configure.ac
  libpcre2-8.pc.in
  libpcre2-16.pc.in
  libpcre2-32.pc.in
  libpcre2-posix.pc.in
  pcre2-config.in
  perltest.sh
  cmake/COPYING-CMAKE-SCRIPTS
  cmake/{*.cmake,*.in}
  m4/ax_pthread.m4
  m4/pcre2_check_vscript.m4
  m4/pcre2_visibility.m4
  m4/pcre2_zos.m4
  doc/p*
  doc/man/*
  doc/html/*
  src/libpcre2-*.sym.in
  )

crlf_files=(
  )

c_files=(
  src/config-cmake.h.in
  src/pcre2.h.in
  src/pcre2_auto_possess.c
  src/pcre2_chartables.c.dist
  src/pcre2_chartables.c.ebcdic-1047-nl15
  src/pcre2_chartables.c.ebcdic-1047-nl25
  src/pcre2_chkdint.c
  src/pcre2_compile.c
  src/pcre2_compile.h
  src/pcre2_compile_cgroup.c
  src/pcre2_compile_class.c
  src/pcre2_config.c
  src/pcre2_context.c
  src/pcre2_convert.c
  src/pcre2_dfa_match.c
  src/pcre2_dftables.c
  src/pcre2_error.c
  src/pcre2_extuni.c
  src/pcre2_find_bracket.c
  src/pcre2_fuzzsupport.c
  src/pcre2_internal.h
  src/pcre2_intmodedep.h
  src/pcre2_jit_char_inc.h
  src/pcre2_jit_compile.c
  src/pcre2_jit_match_inc.h
  src/pcre2_jit_misc_inc.h
  src/pcre2_jit_simd_inc.h
  src/pcre2_jit_test.c
  src/pcre2_maketables.c
  src/pcre2_match.c
  src/pcre2_match_data.c
  src/pcre2_match_next.c
  src/pcre2_newline.c
  src/pcre2_ord2utf.c
  src/pcre2_pattern_info.c
  src/pcre2_printint_inc.h
  src/pcre2_script_run.c
  src/pcre2_serialize.c
  src/pcre2_string_utils.c
  src/pcre2_study.c
  src/pcre2_substitute.c
  src/pcre2_substring.c
  src/pcre2_tables.c
  src/pcre2_ucd.c
  src/pcre2_ucp.h
  src/pcre2_ucptables_inc.h
  src/pcre2_util.h
  src/pcre2_valid_utf.c
  src/pcre2_xclass.c
  src/pcre2demo.c
  src/pcre2grep.c
  src/pcre2posix.c
  src/pcre2posix.h
  src/pcre2posix_test.c
  src/pcre2test.c
  src/pcre2test_inc.h
  )

echo Detrailing
perl maint/Detrail "${txt_files[@]}" "${c_files[@]}"

echo Validating all text
perl maint/CheckTxt "${txt_files[@]}"
perl maint/CheckTxt -ascii "${c_files[@]}"
perl maint/CheckTxt -crlf "${crlf_files[@]}"

SLJIT_COMMIT=$(git rev-parse HEAD:deps/sljit 2>/dev/null)
if [ -z "$SLJIT_COMMIT" ] ; then
  echo "Warning: could not find deps/sljit in the tree; not updating build.zig.zon"
elif grep -q "sljit.git#$SLJIT_COMMIT" build.zig.zon ; then
  echo "SLJIT pinned in build.zig.zon to $SLJIT_COMMIT"
elif ! command -v zig >/dev/null 2>&1 ; then
  echo "Warning: zig is not executable; not updating build.zig.zon"
else
  echo "Updating SLJIT pin in build.zig.zon to $SLJIT_COMMIT"
  zig fetch --save=sljit "git+https://github.com/zherczeg/sljit.git#$SLJIT_COMMIT"
  if [ $? != 0 ] ; then exit 1; fi
fi

# Verify the version number in the Bazel file
if ! grep -E "version = \"$CURRENT_RELEASE\"" MODULE.bazel >/dev/null ; then
  echo "Version number in MODULE.bazel does not match current release"
  exit 1
fi

echo Done

#End
