Copy and split OboParser into parts

Copied from https://github.com/nfdi4plants/ISADotNet/blob/developer/src/ISADotNet.QueryModel/Obo.fs
ISA.NET dependency was necessary.

FsOboParser.sln

@@ -0,0 +1,25 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio Version 17
+VisualStudioVersion = 17.0.31903.59
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{F2A71F9B-5D33-465A-A702-920D77279786}") = "FsOboParser", "src\FsOboParser\FsOboParser.fsproj", "{7812F4E0-128E-437C-92CF-84C9F621C459}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{7812F4E0-128E-437C-92CF-84C9F621C459}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{7812F4E0-128E-437C-92CF-84C9F621C459}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{7812F4E0-128E-437C-92CF-84C9F621C459}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{7812F4E0-128E-437C-92CF-84C9F621C459}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+	GlobalSection(ExtensibilityGlobals) = postSolution
+		SolutionGuid = {54B9E6DB-7B93-4B11-AF6D-F46EF21F9781}
+	EndGlobalSection
+EndGlobal

src/FsOboParser/DBXref.fs

@@ -0,0 +1,47 @@
+namespace FsOboParser
+
+open System
+
+
+module Obo =
+
+    //Dbxref definitions take the following form:
+
+    //<dbxref name> {optional-trailing-modifier}
+
+    //or
+
+    //<dbxref name> "<dbxref description>" {optional-trailing-modifier}
+
+    //The dbxref is a colon separated key-value pair. The key should be taken from GO.xrf_abbs but this is not a requirement. 
+    //If provided, the dbxref description is a string of zero or more characters describing the dbxref. 
+    //DBXref descriptions are rarely used and as of obof1.4 are discouraged.
+
+    //Dbxref lists are used when a tag value must contain several dbxrefs. Dbxref lists take the following form:
+
+    //[<dbxref definition>, <dbxref definition>, ...]
+
+    //The brackets may contain zero or more comma separated dbxref definitions. An example of a dbxref list can be seen in the GO def for "ribonuclease MRP complex":
+
+    //def: "A ribonucleoprotein complex that contains an RNA molecule of the snoRNA family, and cleaves the rRNA precursor as part of rRNA transcript processing. It also has other roles: In S. cerevisiae it is involved in cell cycle-regulated degradation of daughter cell-specific mRNAs, while in mammalian cells it also enters the mitochondria and processes RNAs to create RNA primers for DNA replication." [GOC:sgd_curators, PMID:10690410, Add to Citavi project by Pubmed ID PMID:14729943, Add to Citavi project by Pubmed ID PMID:7510714] Add to Citavi project by Pubmed ID
+
+    //Note that the trailing modifiers (like all trailing modifiers) do not need to be decoded or round-tripped by parsers; trailing modifiers can always be optionally ignored. However, all parsers must be able to gracefully ignore trailing modifiers. It is important to recognize that lines which accept a dbxref list may have a trailing modifier for each dbxref in the list, and another trailing modifier for the line itself.
+    type DBXref = {
+        Name        : string
+        Description : string
+        Modifiers   : string
+    }
+
+    let trimComment (line : string) = 
+        line.Split('!').[0].Trim()
+
+    let private xrefRegex = 
+        Text.RegularExpressions.Regex("""(?<xrefName>^([^"{])*)(\s?)(?<xrefDescription>\"(.*?)\")?(\s?)(?<xrefModifiers>\{(.*?)}$)?""")
+
+    let parseDBXref (v:string) =
+        let matches = xrefRegex.Match(v.Trim()).Groups
+        {
+            Name = matches.Item("xrefName").Value
+            Description = matches.Item("xrefDescription").Value
+            Modifiers = matches.Item("xrefModifiers").Value
+        }

src/FsOboParser/FastOboGraph.fs

@@ -0,0 +1,111 @@
+namespace FsOboParser
+
+open Obo
+
+
+////########################################
+//// Definition of OboGraph
+
+
+//module FastOboGraph =
+
+//    /// Obo Term as node
+//    [<StructuredFormatDisplay("{PrettyString}")>]
+//    type OboNode = { 
+//        Id : int
+//        Name : string
+//        NameSpace : string
+//        OntologyId : string // GO:
+//        }
+//        with
+//        member this.PrettyString = sprintf "%s:%07i | %s {%s}" this.OntologyId this.Id this.Name this.NameSpace
+//        interface INode<int>
+//            with member this.Id = this.Id
+
+
+//    /// Creates OboNode
+//    let createOboNode id name nameSpace ontologyId =
+//        {Id = id; Name = name; NameSpace = nameSpace; OntologyId = ontologyId; }
+
+
+
+//    type OboEdgeType =
+//        | Is_A
+//        | Part_Of
+
+//    [<StructuredFormatDisplay("{PrettyString}")>]
+//    type OboEdge = { 
+//        Id : int
+//        SourceId :int
+//        TargetId :int } 
+//        with
+//        member this.PrettyString =  if this.Id = this.SourceId then
+//                                        sprintf "o---> %07i | (%i)" this.Id this.TargetId
+//                                    else 
+//                                        sprintf "%07i <---o | (%i)" this.Id this.TargetId
+//        interface IEdge<int> with
+//            member this.Id = this.Id
+//            member this.SourceId = this.SourceId
+//            member this.TargetId = this.TargetId
+
+
+//    /// Creates OboEdge
+//    let createOboEdge id sourceId targetId =
+//        {Id = id; SourceId = sourceId; TargetId = targetId}
+
+
+//    type oboAdjacencyNode = AdjacencyNode<OboNode,OboEdge,int>
+
+
+
+//    /// Splits String s at ":", returns sa.[1]
+//    let tryIdToInt str =
+//        match str with
+//        | Regex.RegexValue @"GO:(?<goId>[\d]+)" [ goId; ] -> Some( int goId )
+//        | _ -> None
+
+//    let idToInt str =
+//        match tryIdToInt str with
+//        | Some v -> v
+//        | None   -> failwithf "%s invaild GO id" str
+
+//    let private oboIdStringToInt s =
+//        let sa = String.split ':' s
+//        if sa.Length > 1 then
+//            sa.[1] |> int
+//        else
+//            -1
+
+//    /// Creates fromOboTerm from oboTerm startIndex
+//    let fromOboTerm (obo: OboTerm) (startIndex: int) =
+//        let nodeId = oboIdStringToInt obo.Id
+//        let node   = createOboNode nodeId obo.Name obo.Namespace
+//        let edges = 
+//            obo.IsA
+//            |> List.mapi (fun i edId -> let edgeTargetId = oboIdStringToInt edId
+//                                        createOboEdge (i+startIndex) nodeId edgeTargetId
+//                            )
+//        (node,edges,(startIndex + obo.IsA.Length))
+
+
+//    /// Creates OboEnumerator from oboNode oboEdge
+//    let oboTermToOboGraph (input: seq<OboTerm>) = //: seq<oboAdjacencyNode> =
+//        let en = input.GetEnumerator()
+//        let rec loop (en:System.Collections.Generic.IEnumerator<OboTerm>) acc  =
+//            seq { 
+//                match en.MoveNext() with
+//                | true -> let cNode,cEdges,cIndex = fromOboTerm en.Current acc
+
+//                            yield (cNode,cEdges)
+//                            yield! loop en cIndex
+//                | false -> ()
+//                }
+//        loop en 0
+
+
+//    /// Reads obo file 
+//    let readFile path =
+//        FileIO.readFile path
+//        |> parseOboTerms
+//        |> oboTermToOboGraph
+//        |> Seq.toList

src/FsOboParser/FsOboParser.fsproj

@@ -0,0 +1,21 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <TargetFramework>net6.0</TargetFramework>
+    <GenerateDocumentationFile>true</GenerateDocumentationFile>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <Compile Include="DBXref.fs" />
+    <Compile Include="TermSynonym.fs" />
+    <Compile Include="OboTerm.fs" />
+    <Compile Include="OboTypeDef.fs" />
+    <Compile Include="OboOntology.fs" />
+    <Compile Include="FastOboGraph.fs" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <PackageReference Include="ISADotNet" Version="0.6.1" />
+  </ItemGroup>
+
+</Project>