Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

recoll: replace antiword with abiword #236512

Closed
wants to merge 3 commits into from
Closed

recoll: replace antiword with abiword #236512

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7fff506
recoll: factor out dependency list
Jun 7, 2023
52b9f35
recoll: use wrapProgram to set $PATH for recoll, recollindex
Jun 7, 2023
1bc8775
recoll: replace antiword with abiword
Jun 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
64 changes: 44 additions & 20 deletions pkgs/applications/search/recoll/default.nix
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,9 @@
{ stdenv
, fetchurl
, fetchpatch
, lib
, mkDerivation
, antiword
, abiword
, bison
, catdoc
, chmlib
Expand Down Expand Up @@ -35,6 +36,34 @@
, withGui ? true
}:

let filters = {
# "binary-name = package" where:
# - "${package}/bin/${binary-name}" is the full path to the binary
# - occurrences of `"${binary-name}"` in recoll's filters should be fixed up
abiword = abiword;
awk = gawk;
catppt = catdoc;
djvused = djvulibre;
djvutxt = djvulibre;
egrep = gnugrep;
groff = groff;
gunzip = gzip;
iconv = libiconv;
pdftotext = poppler_utils;
ps2ascii = ghostscript;
sed = gnused;
tar = gnutar;
unzip = unzip;
xls2csv = catdoc;
xsltproc = libxslt;
unrtf = unrtf;
untex = untex;
wpd2html = libwpd;
perl = perl.passthru.withPackages (p: [ p.ImageExifTool ]);
};
filterPath = lib.makeBinPath (map lib.getBin (builtins.attrValues filters));
in

mkDerivation rec {
pname = "recoll";
version = "1.33.4";
Expand Down Expand Up @@ -62,6 +91,14 @@ mkDerivation rec {
patches = [
# fix "No/bad main configuration file" error
./fix-datadir.patch

# use abiword instead of antiword; allows indexing "fast-saved"
# MSWORD files (which is most of them) instead of failing with
# "Word2: fast saved documents are not supported yet"
(fetchpatch {
url = "https://trac.xapian.org/raw-attachment/ticket/383/abiword.patch";
hash = "sha256-AOTM36cQhvCnuANjYTfQIT5wmq96BHKQrag+/7J9NYs=";
})
];

nativeBuildInputs = [
Expand Down Expand Up @@ -93,28 +130,15 @@ mkDerivation rec {
substituteInPlace $out/share/recoll/filters/rclconfig.py --replace /usr/share/recoll $out/share/recoll
for f in $out/share/recoll/filters/* ; do
if [[ ! "$f" =~ \.zip$ ]]; then
substituteInPlace $f --replace '"antiword"' '"${lib.getBin antiword}/bin/antiword"'
substituteInPlace $f --replace '"awk"' '"${lib.getBin gawk}/bin/awk"'
substituteInPlace $f --replace '"catppt"' '"${lib.getBin catdoc}/bin/catppt"'
substituteInPlace $f --replace '"djvused"' '"${lib.getBin djvulibre}/bin/djvused"'
substituteInPlace $f --replace '"djvutxt"' '"${lib.getBin djvulibre}/bin/djvutxt"'
substituteInPlace $f --replace '"egrep"' '"${lib.getBin gnugrep}/bin/egrep"'
substituteInPlace $f --replace '"groff"' '"${lib.getBin groff}/bin/groff"'
substituteInPlace $f --replace '"gunzip"' '"${lib.getBin gzip}/bin/gunzip"'
substituteInPlace $f --replace '"iconv"' '"${lib.getBin libiconv}/bin/iconv"'
substituteInPlace $f --replace '"pdftotext"' '"${lib.getBin poppler_utils}/bin/pdftotext"'
'' + lib.concatStrings (lib.mapAttrsToList (k: v: (''
substituteInPlace $f --replace '"${k}"' '"${lib.getBin v}/bin/${k}"'
'')) filters) + ''
substituteInPlace $f --replace '"pstotext"' '"${lib.getBin ghostscript}/bin/ps2ascii"'
substituteInPlace $f --replace '"sed"' '"${lib.getBin gnused}/bin/sed"'
substituteInPlace $f --replace '"tar"' '"${lib.getBin gnutar}/bin/tar"'
substituteInPlace $f --replace '"unzip"' '"${lib.getBin unzip}/bin/unzip"'
substituteInPlace $f --replace '"xls2csv"' '"${lib.getBin catdoc}/bin/xls2csv"'
substituteInPlace $f --replace '"xsltproc"' '"${lib.getBin libxslt}/bin/xsltproc"'
substituteInPlace $f --replace '"unrtf"' '"${lib.getBin unrtf}/bin/unrtf"'
substituteInPlace $f --replace '"untex"' '"${lib.getBin untex}/bin/untex"'
substituteInPlace $f --replace '"wpd2html"' '"${lib.getBin libwpd}/bin/wpd2html"'
substituteInPlace $f --replace /usr/bin/perl ${lib.getBin perl}/bin/perl
substituteInPlace $f --replace /usr/bin/perl ${lib.getBin (perl.passthru.withPackages (p: [ p.ImageExifTool ]))}/bin/perl
fi
done
wrapProgram $out/bin/recoll --prefix PATH : "${filterPath}"
wrapProgram $out/bin/recollindex --prefix PATH : "${filterPath}"
wrapProgram $out/share/recoll/filters/rclaudio.py \
--prefix PYTHONPATH : $PYTHONPATH
wrapProgram $out/share/recoll/filters/rclimg \
Expand Down