47 lines
1.4 KiB
Nix
47 lines
1.4 KiB
Nix
|
{
|
||
|
|
description = "Tooling for turning datasheet PDFs into text";
|
||
|
|
|
||
|
|
inputs.nixpkgs.url =
|
||
|
|
"github:NixOS/nixpkgs/a50de1b7d8a586adc18d2395c19de7d6058e6030";
|
||
|
|
|
||
|
|
outputs = { self, nixpkgs }:
|
||
|
|
let
|
||
|
|
systems = [ "x86_64-linux" "aarch64-linux" "x86_64-darwin" "aarch64-darwin" ];
|
||
|
|
forAllSystems = f:
|
||
|
|
nixpkgs.lib.genAttrs systems (system: f nixpkgs.legacyPackages.${system});
|
||
|
|
in
|
||
|
|
{
|
||
|
|
devShells = forAllSystems (pkgs: {
|
||
|
|
default = pkgs.mkShell {
|
||
|
|
name = "datasheet-to-text";
|
||
|
|
|
||
|
|
packages = with pkgs; [
|
||
|
|
# Split / merge / inspect PDFs losslessly.
|
||
|
|
# qpdf --split-pages=1 in.pdf out-%d.pdf
|
||
|
|
# qpdf in.pdf --pages . 12-34 -- out.pdf
|
||
|
|
qpdf
|
||
|
|
|
||
|
|
# pdfseparate, pdfunite, pdftotext, pdfinfo, pdfimages, pdftoppm
|
||
|
|
poppler-utils
|
||
|
|
|
||
|
|
# mutool: draw/extract/convert, good structured text output
|
||
|
|
# mutool draw -F text -o out.txt in.pdf 12-34
|
||
|
|
mupdf
|
||
|
|
|
||
|
|
# Crop/trim rendered pages down to individual figures.
|
||
|
|
# magick in.png -crop WxH+X+Y +repage out.png
|
||
|
|
imagemagick
|
||
|
|
|
||
|
|
# Runs tools/extract-figures.py (stdlib only).
|
||
|
|
python3
|
||
|
|
];
|
||
|
|
|
||
|
|
shellHook = ''
|
||
|
|
echo "datasheet-to-text shell"
|
||
|
|
echo " qpdf $(qpdf --version | head -1 | grep -o '[0-9.]*$') pdftotext mutool magick python3"
|
||
|
|
'';
|
||
|
|
};
|
||
|
|
});
|
||
|
|
};
|
||
|
|
}
|