From 60bf249d137f45cd6b2101036011e439cd6f912c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sandro=20J=C3=A4ckel?= Date: Thu, 23 Jul 2026 21:25:12 +0200 Subject: [PATCH 1/3] nltk-data: 0-unstable-2024-07-29 -> 0-unstable-2026-07-01 Diff: https://github.com/nltk/nltk_data/compare/cfe82914f3c2d24363687f1db3b05e8b9f687e2b...550b6625bcef1f2abff2ff770a5a0d272c9c6b2a --- pkgs/tools/text/nltk-data/default.nix | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) diff --git a/pkgs/tools/text/nltk-data/default.nix b/pkgs/tools/text/nltk-data/default.nix index ee919adfc0ac..81ef143826d5 100644 --- a/pkgs/tools/text/nltk-data/default.nix +++ b/pkgs/tools/text/nltk-data/default.nix @@ -7,7 +7,7 @@ }: let base = { - version = "0-unstable-2024-07-29"; + version = "0-unstable-2026-07-01"; nativeBuildInputs = [ unzip ]; dontBuild = true; dontFixup = true; @@ -30,9 +30,10 @@ let }: let src = fetchFromGitHub { + name = "nltk-${location}"; owner = "nltk"; repo = "nltk_data"; - rev = "cfe82914f3c2d24363687f1db3b05e8b9f687e2b"; + rev = "550b6625bcef1f2abff2ff770a5a0d272c9c6b2a"; inherit hash; sparseCheckout = [ "packages/${location}/${pname}.zip" ]; }; @@ -60,7 +61,7 @@ let makeNltkDataPackage { inherit pname; location = "chunkers"; - hash = "sha256-kemjqaCM9hlKAdMw8oVJnp62EAC9rMQ50dKg7wlAwEc="; + hash = "sha256-+n0TkS+/NHk0OqFZNQBLIcO/9uw56Mn7/AyNkRDGZEQ="; }; makeCorpus = @@ -68,7 +69,7 @@ let makeNltkDataPackage { inherit pname; location = "corpora"; - hash = "sha256-8lMjW5YI8h6dHJ/83HVY2OYGDyKPpgkUAKPISiAKqqk="; + hash = "sha256-7uiTXZ+eMyBtH135NsYoAjLV6R/DG2hVV+RJwYDmu50="; }; makeGrammar = @@ -76,7 +77,7 @@ let makeNltkDataPackage { inherit pname; location = "grammars"; - hash = "sha256-pyLEcX3Azv8j1kCGvVYonuiNgVJxtWt7veU0S/yNbIM="; + hash = "sha256-KoZ1q0F2X7bSFdbw1qK/jzZ3iuMJXTYHfogylO7nHEY="; }; makeHelp = @@ -84,7 +85,7 @@ let makeNltkDataPackage { inherit pname; location = "help"; - hash = "sha256-97mYLNES5WujLF5gD8Ul4cJ6LqSzz+jDzclUsdBeHNE="; + hash = "sha256-2x3kemPdipHAj0TGYCm6Il5Aapx+fuo/jlNT9+XWbss="; }; makeMisc = @@ -92,7 +93,7 @@ let makeNltkDataPackage { inherit pname; location = "misc"; - hash = "sha256-XtizfEsc8TYWqvvC/eSFdha2ClC5/ZiJM8nue0vXLb4="; + hash = "sha256-edBgrWM+eQgEGWq7oBHTebtvJPZcofCzzXSu3S9Fa1o="; }; makeModel = @@ -100,7 +101,7 @@ let makeNltkDataPackage { inherit pname; location = "models"; - hash = "sha256-iq3weEgCci6rgLW2j28F2eRLprJtInGXKe/awJPSVG4="; + hash = "sha256-uTRr9pBfL1KZ7z8WTQPAiWlMn/os4ISa9tj/Si/RmtI="; }; makeTagger = @@ -108,7 +109,7 @@ let makeNltkDataPackage { inherit pname; location = "taggers"; - hash = "sha256-tl3Cn2okhBkUtTXvAmFRx72Brez6iTGRdmFTwFmpk3M="; + hash = "sha256-V5bs0JUQgr4ijs2NaF5JXzVwT1e/ZYnlU0TZXeoqfM4="; }; makeTokenizer = @@ -116,7 +117,7 @@ let makeNltkDataPackage { inherit pname; location = "tokenizers"; - hash = "sha256-OzMkruoYbFKqzuimOXIpE5lhHz8tmSqOFoLT+fjdTVg="; + hash = "sha256-V/Qs8wJbCZB8gp5pAAM1JK8aAfcHorNyvAkHUat56uY="; }; makeStemmer = @@ -124,7 +125,7 @@ let makeNltkDataPackage { inherit pname; location = "stemmers"; - hash = "sha256-mNefwOPVJGz9kXV3LV4DuV7FJpNir/Nwg4ujd0CogEk="; + hash = "sha256-6sQQCA8r8jWRFImpiBovUt/IzHjh13W6X8yLpn61cs0="; }; in lib.makeScope newScope (self: { @@ -152,6 +153,7 @@ lib.makeScope newScope (self: { crubadan = makeCorpus "crubadan"; dependency-treebank = makeCorpus "dependency_treebank"; dolch = makeCorpus "dolch"; + english_wordnet = makeCorpus "english_wordnet"; europarl-raw = makeCorpus "europarl_raw"; extended-omw = makeCorpus "extended_omw"; floresta = makeCorpus "floresta"; @@ -170,6 +172,7 @@ lib.makeScope newScope (self: { mac-morpho = makeCorpus "mac_morpho"; machado = makeCorpus "machado"; masc-tagged = makeCorpus "masc_tagged"; + mock_corpus = makeCorpus "mock_corpus"; movie-reviews = makeCorpus "movie_reviews"; mte-teip5 = makeCorpus "mte_teip5"; names = makeCorpus "names"; @@ -178,6 +181,7 @@ lib.makeScope newScope (self: { nps-chat = makeCorpus "nps_chat"; omw = makeCorpus "omw"; omw-1-4 = makeCorpus "omw-1.4"; + omw-2-0 = makeCorpus "omw-2.0"; opinion-lexicon = makeCorpus "opinion_lexicon"; panlex-swadesh = makeCorpus "panlex_swadesh"; paradigms = makeCorpus "paradigms"; From 9494ef5d2cb318175a008b3b7f10b9545a1a1b15 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sandro=20J=C3=A4ckel?= Date: Thu, 23 Jul 2026 22:47:21 +0200 Subject: [PATCH 2/3] python314Packages.nltk: 3.9.4 -> 3.10.0 Diff: https://github.com/nltk/nltk/compare/3.9.4...v3.10.0 --- .../python-modules/nltk/default.nix | 20 ++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/pkgs/development/python-modules/nltk/default.nix b/pkgs/development/python-modules/nltk/default.nix index 9958388f1e3d..1f4b97079bfa 100644 --- a/pkgs/development/python-modules/nltk/default.nix +++ b/pkgs/development/python-modules/nltk/default.nix @@ -5,6 +5,7 @@ fetchFromGitHub, buildPythonPackage, click, + defusedxml, joblib, regex, setuptools, @@ -23,49 +24,53 @@ buildPythonPackage (finalAttrs: { pname = "nltk"; - version = "3.9.4"; + version = "3.10.0"; pyproject = true; src = fetchFromGitHub { owner = "nltk"; repo = "nltk"; - tag = finalAttrs.version; - hash = "sha256-kDfMiqXgLq91zzDjv/qDn0XwQkYRn2sITI6E4pgWe/8="; + tag = "v${finalAttrs.version}"; + hash = "sha256-1iflqb3cOyaviW3IostFCuJtZ9KBZI0n9dfKfqqbcO0="; }; postPatch = '' # In the nix store we trust substituteInPlace nltk/pathsec.py \ - --replace-fail 'if not (target == scoped_root or target.is_relative_to(scoped_root)):' 'if not (target == scoped_root or target.is_relative_to(scoped_root) or target.is_relative_to("/nix/store")):' + --replace-fail 'if not (target == scoped_root or target.is_relative_to(scoped_root)):' \ + 'if not (target == scoped_root or target.is_relative_to(scoped_root) or target.is_relative_to("/nix/store")):' \ + --replace-fail ' "/usr/share/nltk_data", ' ' "/usr/share/nltk_data", "/nix/store", ' ''; build-system = [ setuptools ]; dependencies = [ click + defusedxml joblib regex tqdm ]; - # Use new passthru function to pass dependencies required for testing preInstallCheck = '' export NLTK_DATA=${ nltk.dataDir ( d: with d; [ averaged-perceptron-tagger-eng averaged-perceptron-tagger-rus + bcp47 brown cess-cat cess-esp conll2007 floresta gutenberg + ieer inaugural indian large-grammars nombank-1-0 - omw-1-4 + omw-2-0 pl196x porter-test ptb @@ -114,9 +119,10 @@ buildPythonPackage (finalAttrs: { }; meta = { + changelog = "https://github.com/nltk/nltk/blob/${finalAttrs.src.tag}/ChangeLog"; description = "Natural Language Processing ToolKit"; mainProgram = "nltk"; - homepage = "http://nltk.org/"; + homepage = "https://nltk.org/"; license = lib.licenses.asl20; maintainers = [ lib.maintainers.bengsparks ]; }; From f107f71070e41d0b43b338ecf8289a2f136db3c8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sandro=20J=C3=A4ckel?= Date: Thu, 23 Jul 2026 23:06:51 +0200 Subject: [PATCH 3/3] paperless-ngx: relax nltk dependency --- pkgs/by-name/pa/paperless-ngx/package.nix | 1 + 1 file changed, 1 insertion(+) diff --git a/pkgs/by-name/pa/paperless-ngx/package.nix b/pkgs/by-name/pa/paperless-ngx/package.nix index c926b86282bf..e75259f543e6 100644 --- a/pkgs/by-name/pa/paperless-ngx/package.nix +++ b/pkgs/by-name/pa/paperless-ngx/package.nix @@ -117,6 +117,7 @@ pythonPackages.buildPythonApplication (finalAttrs: { "drf-spectacular-sidecar" "python-dotenv" "gotenberg-client" + "nltk" "redis" "scikit-learn" "tika-client"