add tests, some docs and CI

.github/dependabot.yml

@@ -0,0 +1,7 @@
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/" # Location of package manifests
+    schedule:
+      interval: "weekly"

.github/workflows/CI.yml

@@ -0,0 +1,40 @@
+name: CI
+on:
+  push:
+    branches:
+      - main
+    tags: ['*']
+  pull_request:
+concurrency:
+  # Skip intermediate builds: always.
+  # Cancel intermediate builds: only if it is a pull request build.
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ startsWith(github.ref, 'refs/pull/') }}
+jobs:
+  test:
+    name: Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        version:
+          - '1.6'
+          - '1.9'
+          - 'nightly'
+        os:
+          - ubuntu-latest
+        arch:
+          - x64
+    steps:
+      - uses: actions/checkout@v3
+      - uses: julia-actions/setup-julia@v1
+        with:
+          version: ${{ matrix.version }}
+          arch: ${{ matrix.arch }}
+      - uses: julia-actions/cache@v1
+      - uses: julia-actions/julia-buildpkg@v1
+      - uses: julia-actions/julia-runtest@v1
+      - uses: julia-actions/julia-processcoverage@v1
+      - uses: codecov/codecov-action@v3
+        with:
+          files: lcov.info

.github/workflows/CompatHelper.yml

@@ -0,0 +1,16 @@
+name: CompatHelper
+on:
+  schedule:
+    - cron: 0 0 * * *
+  workflow_dispatch:
+jobs:
+  CompatHelper:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Pkg.add("CompatHelper")
+        run: julia -e 'using Pkg; Pkg.add("CompatHelper")'
+      - name: CompatHelper.main()
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          COMPATHELPER_PRIV: ${{ secrets.DOCUMENTER_KEY }}
+        run: julia -e 'using CompatHelper; CompatHelper.main()'

.github/workflows/TagBot.yml

@@ -0,0 +1,15 @@
+name: TagBot
+on:
+  issue_comment:
+    types:
+      - created
+  workflow_dispatch:
+jobs:
+  TagBot:
+    if: github.event_name == 'workflow_dispatch' || github.actor == 'JuliaTagBot'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: JuliaRegistries/TagBot@v1
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          ssh: ${{ secrets.DOCUMENTER_KEY }}

.github/workflows/register.yml

@@ -0,0 +1,16 @@
+name: Register Package
+on:
+  workflow_dispatch:
+    inputs:
+      version:
+        description: Version to register or component to bump
+        required: true
+jobs:
+  register:
+    runs-on: ubuntu-latest
+    permissions:
+        contents: write
+    steps:
+      - uses: julia-actions/RegisterAction@latest
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -0,0 +1,8 @@
+Manifest.toml
+docs/build/
+docs/site/
+*.jl.cov
+*.jl.*.cov
+*.jl.mem
+lcov.info
+LocalPreferences.toml

Project.toml

@@ -1,4 +1,4 @@
-name = "ClapeyronGCIdentifier"
+name = "GCIdentifier"
 uuid = "b7ea765e-cbac-4e4a-9b0d-5427cc302506"
 authors = ["Hon Wa Yew <[email protected]>", "Pierre Walker <[email protected]>", "Andrés Riedemann <[email protected]>"]
 version = "0.1.0"
@@ -8,5 +8,18 @@ ChemicalIdentifiers = "fa4ea961-1416-484e-bda2-883ee1634ba5"
 Clapeyron = "7c7805af-46cc-48c9-995b-ed0ed2dc909a"
 RDKitMinimalLib = "44044271-7623-48dc-8250-42433c44e4b7"
 
+[weakdeps]
+Clapeyron = "7c7805af-46cc-48c9-995b-ed0ed2dc909a"
+
+[extensions]
+GCIdentifierClapeyronExt = "Clapeyron"
+
 [compat]
-Clapeyron = "0.4"
+Clapeyron = "0.4"
+
+[extras]
+Clapeyron = "7c7805af-46cc-48c9-995b-ed0ed2dc909a"
+Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+
+[targets]
+test = ["Test"]

README.md

@@ -1,2 +1,5 @@
-# ClapeyronGCIdentifier
-identifies subgroups, given a SMILES
+# GCIdentifier
+
+identifies subgroups, given a SMILES.
+
+A l

ext/GCIdentifierClapeyronExt.jl

@@ -0,0 +1,19 @@
+module GCIdentifierClapeyronExt
+
+if !isdefined(Base,:get_extension)
+    using Clapeyron
+    using GCIdentifier
+else
+    using ..Clapeyron
+    using ..GCIdentifier
+end
+
+const GC = GCIdentifier
+
+GC.get_grouplist(m::Clapeyron.EoSModel) = GC.get_grouplist(typeof(m))
+GC.get_grouplist(Type{T}) where T <: UNIFAC = GC.UNIFACGroups
+GC.get_grouplist(Type{T}) where T <: SAFTgammaMie = GC.SAFTgammaMieGroups
+GC.get_grouplist(Type{T}) where T <: Joback = GC.JobackGroups
+GC.get_grouplist(Type{T}) where T <: gcPCSAFT = GC.gcPCSAFTgroups
+
+end #module

src/GCIdentifier.jl

@@ -0,0 +1,19 @@
+module GCIdentifier
+using RDKitMinimalLib, ChemicalIdentifiers
+
+@static if !isdefined(Base,:eachsplit)
+    eachsplit(str::AbstractString, dlm; limit::Integer=0, keepempty::Bool=true) = split(str,dlm;limit,keepempty)
+    eachsplit(str::AbstractString; limit::Integer=0, keepempty::Bool=false)  = split(str;limit,keepempty)
+end
+
+split_2(str) = NTuple{2}(eachsplit(str, limit=2))
+split_2(str,dlm) = NTuple{2}(eachsplit(str,dlm, limit=2))
+
+include("group_search.jl")
+include("database/database.jl")
+
+if !isdefined(Base,:get_extension)
+    using Clapeyron
+    include("../ext/GCIdentifierClapeyronExt.jl")
+end
+end # module

src/database/Joback.jl

@@ -1,43 +1,44 @@
-JobackGroups = [raw"[CX4H3]" "-CH3";
-raw"[!R;CX4H2]" "-CH2-";
-raw"[!R;CX4H]" ">CH-";
-raw"[!R;CX4H0]" ">C<";
-raw"[CX3H2][CX3H1]" "CH2=CH-";
-raw"[CX3H1][CX3H1]" "-CH=CH-";
-raw"[$([!R;#6X3H0]);!$([!R;#6X3H0]=[#8])]" "=C<";
-raw"[$([CX2H0](=*)=*)]" "=C=";
-raw"[$([CX2H1]#[!#7])]" "CH";
-raw"[$([CX2H0]#[!#7])]" "C";
-raw"[R;CX4H2]" "ring-CH2-";
-raw"[R;CX4H]" "ring>CH-";
-raw"[R;CX4H0]" "ring>C<";
-raw"[R;CX3H1,cX3H1]" "ring=CH-";
-raw"[$([R;#6X3H0]);!$([R;#6X3H0]=[#8])]" "ring=C<";
-raw"[F]" "-F";
-raw"[Cl]" "-Cl";
-raw"[Br]" "-Br";
-raw"[I]" "-I";
-raw"[OX2H;!$([OX2H]-[#6]=[O]);!$([OX2H]-a)]" "-OH (alcohol)";
-raw"[O;H1;$(O-!@c)]" "-OH (phenol)";
-raw"[OX2H0;!R;!$([OX2H0]-[#6]=[#8])]" "-O- (non-ring)";
-raw"[#8X2H0;R;!$([#8X2H0]~[#6]=[#8])]" "-O- (ring)";
-raw"[$([CX3H0](=[OX1]));!$([CX3](=[OX1])-[OX2]);!R]=O" ">C=O (non-ring)";
-raw"[$([#6X3H0](=[OX1]));!$([#6X3](=[#8X1])~[#8X2]);R]=O" ">C=O (ring)";
-raw"[CH;D2](=O)" "O=CH- (aldehyde)";
-raw"[OX2H]-[C]=O" "-COOH (acid)";
-raw"[#6X3H0;!$([#6X3H0](~O)(~O)(~O))](=[#8X1])[#8X2H0]" "-COO- (ester)";
-raw"[OX1H0;!$([OX1H0]~[#6X3]);!$([OX1H0]~[#7X3]~[#8])]" "=O (other than above)";
-raw"[NX3H2]" "-NH2";
-raw"[NX3H1;!R]" ">NH (non-ring)";
-raw"[#7X3H1;R]" ">NH (ring)";
-raw"[#7X3H0;!$([#7](~O)~O)]" ">N- (non-ring)";
-raw"[#7X2H0;!R]" "-N= (non-ring)";
-raw"[#7X2H0;R]" "-N= (ring)";
-raw"[#7X2H1]" "=NH";
-raw"[#6X2]#[#7X1H0]" "-CN";
-raw"[$([#7X3,#7X3+][!#8])](=[O])~[O-]" "-NO2";
-raw"[SX2H]" "-SH";
-raw"[#16X2H0;!R]" "-S- (non-ring)";
-raw"[#16X2H0;R]" "-S- (ring)"]
+JobackGroups = [GCPair(raw"[CX4H3]","-CH3"),
+GCPair(raw"[!R;CX4H2]","-CH2-"),
+GCPair(raw"[!R;CX4H]",">CH-"),
+GCPair(raw"[!R;CX4H0]",">C<"),
+GCPair(raw"[CX3H2][CX3H1]","CH2=CH-"),
+GCPair(raw"[CX3H1][CX3H1]","-CH=CH-"),
+GCPair(raw"[$([!R;#6X3H0]);!$([!R;#6X3H0]=[#8])]","=C<"),
+GCPair(raw"[$([CX2H0](=*)=*)]","=C="),
+GCPair(raw"[$([CX2H1]#[!#7])]","CH"),
+GCPair(raw"[$([CX2H0]#[!#7])]","C"),
+GCPair(raw"[R;CX4H2]","ring-CH2-"),
+GCPair(raw"[R;CX4H]","ring>CH-"),
+GCPair(raw"[R;CX4H0]","ring>C<"),
+GCPair(raw"[R;CX3H1,cX3H1]","ring=CH-"),
+GCPair(raw"[$([R;#6X3H0]);!$([R;#6X3H0]=[#8])]","ring=C<"),
+GCPair(raw"[F]","-F"),
+GCPair(raw"[Cl]","-Cl"),
+GCPair(raw"[Br]","-Br"),
+GCPair(raw"[I]","-I"),
+GCPair(raw"[OX2H;!$([OX2H]-[#6]=[O]);!$([OX2H]-a)]","-OH (alcohol)"),
+GCPair(raw"[O;H1;$(O-!@c)]","-OH (phenol)"),
+GCPair(raw"[OX2H0;!R;!$([OX2H0]-[#6]=[#8])]","-O- (non-ring)"),
+GCPair(raw"[#8X2H0;R;!$([#8X2H0]~[#6]=[#8])]","-O- (ring)"),
+GCPair(raw"[$([CX3H0](=[OX1]));!$([CX3](=[OX1])-[OX2]);!R]=O",">C=O (non-ring)"),
+GCPair(raw"[$([#6X3H0](=[OX1]));!$([#6X3](=[#8X1])~[#8X2]);R]=O",">C=O (ring)"),
+GCPair(raw"[CH;D2](=O)","O=CH- (aldehyde)"),
+GCPair(raw"[OX2H]-[C]=O","-COOH (acid)"),
+GCPair(raw"[#6X3H0;!$([#6X3H0](~O)(~O)(~O))](=[#8X1])[#8X2H0]","-COO- (ester)"),
+GCPair(raw"[OX1H0;!$([OX1H0]~[#6X3]);!$([OX1H0]~[#7X3]~[#8])]","=O (other than above)"),
+GCPair(raw"[NX3H2]","-NH2"),
+GCPair(raw"[NX3H1;!R]",">NH (non-ring)"),
+GCPair(raw"[#7X3H1;R]",">NH (ring)"),
+GCPair(raw"[#7X3H0;!$([#7](~O)~O)]",">N- (non-ring)"),
+GCPair(raw"[#7X2H0;!R]","-N= (non-ring)"),
+GCPair(raw"[#7X2H0;R]","-N= (ring)"),
+GCPair(raw"[#7X2H1]","=NH"),
+GCPair(raw"[#6X2]#[#7X1H0]","-CN"),
+GCPair(raw"[$([#7X3,#7X3+][!#8])](=[O])~[O-]","-NO2"),
+GCPair(raw"[SX2H]","-SH"),
+GCPair(raw"[#16X2H0;!R]","-S- (non-ring)"),
+GCPair(raw"[#16X2H0;R]","-S- (ring)")
+]
 
 export JobackGroups

src/database/SAFTgammaMie.jl

@@ -1,34 +1,35 @@
-SAFTgammaMieGroups = [raw"[CX4H3]" "CH3";
-raw"[!R;CX4H2]" "CH2";
-raw"[!R;CX4H]" "CH";
-raw"[!R;CX4H0]" "C";
-raw"[cX3;H1]" "aCH";
-raw"[cX3;H0][CX4;H2]" "aCCH2";
-raw"[cX3;H0][CX4;H1]" "aCCH";
-raw"[CX3H2]" "CH2=";
-raw"[!R;CX3H1;!$([CX3H1](=O))]" "CH=";
-raw"[CH2;R]" "cCH2";
-raw"[OX2H]-[C]=O" "COOH";
-raw"[#6X3H0;!$([#6X3H0](~O)(~O)(~O))](=[#8X1])[#8X2H0]" "COO";
-raw"[OX2H;!$([OX2H]-[#6]=[O]);!$([OX2H]-a)]" "OH";
-raw"[CX4;H2;!R][OH1]" "CH2OH";
-raw"[CX4;H1;!R][OH1]" "CHOH";
-raw"[NX3H2]" "NH2";
-raw"[NX3H1;!R]" "NH";
-raw"[#7X3H0;!$([#7](~O)~O)]" "N";
-raw"[#7X3H1;R]" "cNH";
-raw"[#7X3H0;R]" "cN";
-raw"[!R;CX3H0;!$([CX3H0](=O))]" "CH=";
-raw"[cX3;H0][CX4;H3]" "aCCH3";
-raw"[cX3;H0;R][OX2;H1]" "aCOH";
-raw"[CH1;R]" "cCH";
-raw"[CH1;R][NH1;!R]" "cCHNH";
-raw"[CH1;R][NH0;!R]" "cCHN";
-raw"[cH0][C;!R](=O)[cH0]" "aCCOaC";
-raw"[OX2H]-[C](=O)[cH0]" "aCCOOH";
-raw"[cH0][NH1;!R][cH0]" "aCNHaC";
-raw"[CH3][CX3](=O)" "CH3CO";
-raw"[OH0;!R;$([OH0;!R][CH3;!R]);$([OH0;!R][CH2;!R])]" "eO";
-raw"[OH0;!R;$([OH0;!R][CH2;!R])]" "cO"]
+SAFTgammaMieGroups = [GCPair(raw"[CX4H3]","CH3"),
+GCPair(raw"[!R;CX4H2]","CH2"),
+GCPair(raw"[!R;CX4H]","CH"),
+GCPair(raw"[!R;CX4H0]","C"),
+GCPair(raw"[cX3;H1]","aCH"),
+GCPair(raw"[cX3;H0][CX4;H2]","aCCH2"),
+GCPair(raw"[cX3;H0][CX4;H1]","aCCH"),
+GCPair(raw"[CX3H2]","CH2="),
+GCPair(raw"[!R;CX3H1;!$([CX3H1](=O))]","CH="),
+GCPair(raw"[CH2;R]","cCH2"),
+GCPair(raw"[OX2H]-[C]=O","COOH"),
+GCPair(raw"[#6X3H0;!$([#6X3H0](~O)(~O)(~O))](=[#8X1])[#8X2H0]","COO"),
+GCPair(raw"[OX2H;!$([OX2H]-[#6]=[O]);!$([OX2H]-a)]","OH"),
+GCPair(raw"[CX4;H2;!R][OH1]","CH2OH"),
+GCPair(raw"[CX4;H1;!R][OH1]","CHOH"),
+GCPair(raw"[NX3H2]","NH2"),
+GCPair(raw"[NX3H1;!R]","NH"),
+GCPair(raw"[#7X3H0;!$([#7](~O)~O)]","N"),
+GCPair(raw"[#7X3H1;R]","cNH"),
+GCPair(raw"[#7X3H0;R]","cN"),
+GCPair(raw"[!R;CX3H0;!$([CX3H0](=O))]","CH="),
+GCPair(raw"[cX3;H0][CX4;H3]","aCCH3"),
+GCPair(raw"[cX3;H0;R][OX2;H1]","aCOH"),
+GCPair(raw"[CH1;R]","cCH"),
+GCPair(raw"[CH1;R][NH1;!R]","cCHNH"),
+GCPair(raw"[CH1;R][NH0;!R]","cCHN"),
+GCPair(raw"[cH0][C;!R](=O)[cH0]","aCCOaC"),
+GCPair(raw"[OX2H]-[C](=O)[cH0]","aCCOOH"),
+GCPair(raw"[cH0][NH1;!R][cH0]","aCNHaC"),
+GCPair(raw"[CH3][CX3](=O)","CH3CO"),
+GCPair(raw"[OH0;!R;$([OH0;!R][CH3;!R]);$([OH0;!R][CH2;!R])]","eO"),
+GCPair(raw"[OH0;!R;$([OH0;!R][CH2;!R])]","cO")
+]
 
 export SAFTgammaMieGroups