ericphanson · ericphanson · Feb 11, 2021 · Feb 11, 2021
diff --git a/README.md b/README.md
@@ -3,7 +3,12 @@
 [![Build Status](https://github.com/ericphanson/LicenseCheck.jl/workflows/CI/badge.svg)](https://github.com/ericphanson/LicenseCheck.jl/actions)
 [![Coverage](https://codecov.io/gh/ericphanson/LicenseCheck.jl/branch/master/graph/badge.svg)](https://codecov.io/gh/ericphanson/LicenseCheck.jl)
 
-Exports a single Julia function `licensecheck` which wraps some of the functionality of the Go library [licensecheck](https://github.com/google/licensecheck) which takes a single string argument `text` and returns a vector of the names of licenses (in fact, the "license ID"s) matched in `text` and the percent of the text covered by these matches. See the docstring of `licensecheck` for more details.
+This package exposes some simple license-checking capabilities in Julia.
+
+* Exports a Julia function `licensecheck` which wraps some of the functionality of the Go library [licensecheck](https://github.com/google/licensecheck). This function takes a single string argument `text` and returns a vector of the names of licenses (in fact, the SPDX identifiers of the licenses) matched in `text` and the percent of the text covered by these matches.
+* Also exports `is_osi_approved`, which given an [SDPX 3.10 identifier](https://spdx.dev/ids/), checks if the corresponding license is [OSI approved](https://opensource.org/licenses).
+
+See the docstrings for more details.
 
 Note that the licensecheck library is available under a BSD-3-Clause license (<https://github.com/google/licensecheck/blob/v0.3.1/LICENSE>), while the wrapping code here is MIT licensed.
 
@@ -14,6 +19,9 @@ julia> using LicenseCheck
 
 julia> text = read(joinpath(pkgdir(LicenseCheck), "LICENSE"), String);
 
-julia> licensecheck(text)
+julia> results = licensecheck(text)
 (licenses = ["MIT"], percent_covered = 98.82352941176471)
+
+julia> all(is_osi_approved, results.licenses)
+true
 ```
diff --git a/generate_osi_list/Manifest.toml b/generate_osi_list/Manifest.toml
@@ -0,0 +1,101 @@
+# This file is machine-generated - editing it directly is not advised
+
+[[Artifacts]]
+uuid = "56f22d72-fd6d-98f1-02f0-08ddc0907c33"
+
+[[Base64]]
+uuid = "2a0f44e3-6c83-55bd-87e4-b1978d98bd5f"
+
+[[Dates]]
+deps = ["Printf"]
+uuid = "ade2ca70-3891-5945-98fb-dc099432e06a"
+
+[[HTTP]]
+deps = ["Base64", "Dates", "IniFile", "MbedTLS", "Sockets", "URIs"]
+git-tree-sha1 = "942c1a9c750bbe79912b7bd060a420932afd35b8"
+uuid = "cd3eb016-35fb-5094-929b-558a96fad6f3"
+version = "0.9.3"
+
+[[IniFile]]
+deps = ["Test"]
+git-tree-sha1 = "098e4d2c533924c921f9f9847274f2ad89e018b8"
+uuid = "83e8ac13-25f8-5344-8a64-a9f2b223428f"
+version = "0.5.0"
+
+[[InteractiveUtils]]
+deps = ["Markdown"]
+uuid = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
+
+[[JSON3]]
+deps = ["Dates", "Mmap", "Parsers", "StructTypes", "UUIDs"]
+git-tree-sha1 = "961ef1c3e5c8a595d5bec270a9007429ef12ed10"
+uuid = "0f8b85d8-7281-11e9-16c2-39a750bddbf1"
+version = "1.5.1"
+
+[[Libdl]]
+uuid = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
+
+[[Logging]]
+uuid = "56ddb016-857b-54e1-b83d-db4d58db5568"
+
+[[Markdown]]
+deps = ["Base64"]
+uuid = "d6f4376e-aef5-505a-96c1-9c027394607a"
+
+[[MbedTLS]]
+deps = ["Dates", "MbedTLS_jll", "Random", "Sockets"]
+git-tree-sha1 = "1c38e51c3d08ef2278062ebceade0e46cefc96fe"
+uuid = "739be429-bea8-5141-9913-cc70e7f3736d"
+version = "1.0.3"
+
+[[MbedTLS_jll]]
+deps = ["Artifacts", "Libdl"]
+uuid = "c8ffd9c3-330d-5841-b78e-0817d7145fa1"
+
+[[Mmap]]
+uuid = "a63ad114-7e13-5084-954f-fe012c677804"
+
+[[Parsers]]
+deps = ["Dates"]
+git-tree-sha1 = "50c9a9ed8c714945e01cd53a21007ed3865ed714"
+uuid = "69de0a69-1ddd-5017-9359-2bf0b02dc9f0"
+version = "1.0.15"
+
+[[Printf]]
+deps = ["Unicode"]
+uuid = "de0858da-6303-5e67-8744-51eddeeeb8d7"
+
+[[Random]]
+deps = ["Serialization"]
+uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
+
+[[SHA]]
+uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce"
+
+[[Serialization]]
+uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
+
+[[Sockets]]
+uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
+
+[[StructTypes]]
+deps = ["Dates", "UUIDs"]
+git-tree-sha1 = "65a43f5218197bc7091b76bc273a5e323a1d7b0d"
+uuid = "856f2bd8-1eba-4b0a-8007-ebc267875bd4"
+version = "1.2.3"
+
+[[Test]]
+deps = ["InteractiveUtils", "Logging", "Random", "Serialization"]
+uuid = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+
+[[URIs]]
+git-tree-sha1 = "7855809b88d7b16e9b029afd17880930626f54a2"
+uuid = "5c2747f8-b7ea-4ff2-ba2e-563bfd36b1d4"
+version = "1.2.0"
+
+[[UUIDs]]
+deps = ["Random", "SHA"]
+uuid = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
+
+[[Unicode]]
+uuid = "4ec0a83e-493e-50e2-b9ac-8f72acf5a8f5"
diff --git a/generate_osi_list/Project.toml b/generate_osi_list/Project.toml
@@ -0,0 +1,3 @@
+[deps]
+HTTP = "cd3eb016-35fb-5094-929b-558a96fad6f3"
+JSON3 = "0f8b85d8-7281-11e9-16c2-39a750bddbf1"
diff --git a/generate_osi_list/README.md b/generate_osi_list/README.md
@@ -0,0 +1,7 @@
+# README
+
+The code in [`generate.jl`](./generate.jl) generates the file `src/OSI_LICENSES.jl` by
+parsing the SDPX 3.10 list of OSI approved licenses, which itself is available under a
+Creative Commons Attribution 3.0 (SPDX License ID CC-BY-3.0) license.
+
+This code was run on Julia 1.6-rc1 (and so the Manifest is valid for that version of Julia).
diff --git a/generate_osi_list/generate.jl b/generate_osi_list/generate.jl
@@ -0,0 +1,25 @@
+using JSON3, HTTP
+
+url = "https://raw.githubusercontent.com/spdx/license-list-data/v3.10/json/licenses.json"
+r = HTTP.request("GET", url)
+spdx = JSON3.read(String(r.body))
+
+@assert spdx.licenseListVersion == "3.10"
+
+osi_licenses = sort!([lic.licenseId
+                      for lic in spdx.licenses
+                      if lic.isOsiApproved && !lic.isDeprecatedLicenseId])
+
+open(joinpath(@__DIR__, "..", "src", "OSI_LICENSES.jl"); write=true) do io
+    header = """
+            # THIS FILE IS MACHINE-GENERATED
+            # See `../generate_osi_list` for more information."""
+    start = "const OSI_LICENSES = Set(["
+    spaces = " "^textwidth(start)
+    println(io, header)
+    println(io, start, "\"", osi_licenses[1], "\",")
+    for id in osi_licenses[2:(end - 1)]
+        println(io, spaces, "\"", id, "\",")
+    end
+    return println(io, spaces, "\"", osi_licenses[end], "\"])")
+end
diff --git a/src/LicenseCheck.jl b/src/LicenseCheck.jl
@@ -2,16 +2,18 @@ module LicenseCheck
 
 using licensecheck_jll: licensecheck_jll
 
-export licensecheck
+export licensecheck, is_osi_approved
+
+include("OSI_LICENSES.jl")
 
 """
     licensecheck(text::String) -> @NamedTuple{licenses::Vector{String}, percent_covered::Float64}
 
-Returns a vector of the names of licenses (in fact, the "license ID"s) matched in `text` and the percent of the text covered by these matches.
+Returns a vector of the names of licenses (more specifically, the SPDX 3.10 license identifiers) matched in `text` and the percent of the text covered by these matches.
 
-The full list of license IDs is located at <https://github.com/google/licensecheck/blob/v0.3.1/licenses/README.md>, and includes the SDPX 3.10 licenses, <https://github.com/spdx/license-list-data/tree/v3.10/text>.
+The full list of license IDs is located at [https://github.com/google/licensecheck/blob/v0.3.1/licenses/README.md](https://github.com/google/licensecheck/blob/v0.3.1/licenses/README.md), and includes the SDPX 3.10 licenses, [https://github.com/spdx/license-list-data/tree/v3.10/text](https://github.com/spdx/license-list-data/tree/v3.10/text).
 
-This provides some of the functionality of `licensecheck.Scan` in the original Go library (<https://github.com/google/licensecheck>).
+This provides some of the functionality of `licensecheck.Scan` in the original Go library ([https://github.com/google/licensecheck](https://github.com/google/licensecheck)).
 
 ## Example
 
@@ -32,4 +34,26 @@ function licensecheck(text::String)
             percent_covered=percent_covered)
 end
 
+"""
+    is_osi_approved(spdx_identifier::String) -> Bool
+
+Checks if a [SDPX 3.10 identifier](https://spdx.dev/ids/) is
+[OSI approved](https://opensource.org/licenses) by checking against an autogenerated list.
+
+!!! warning
+
+    Note that [`licensecheck`](@ref) understands a larger number of licenses than
+    SDPX 3.10, and can output results which are not SDPX 3.10 identifiers.
+    Such licenses will yield `is_osi_approved(name) == false` regardless of
+    their OSI standing.
+
+## Example
+
+```julia
+julia> is_osi_approved("MIT")
+true
+```
+"""
+is_osi_approved(spdx_identifier::String) = spdx_identifier ∈ OSI_LICENSES
+
 end
diff --git a/src/OSI_LICENSES.jl b/src/OSI_LICENSES.jl
@@ -0,0 +1,120 @@
+# THIS FILE IS MACHINE-GENERATED
+# See `../generate_osi_list` for more information.
+const OSI_LICENSES = Set(["0BSD",
+                          "AAL",
+                          "AFL-1.1",
+                          "AFL-1.2",
+                          "AFL-2.0",
+                          "AFL-2.1",
+                          "AFL-3.0",
+                          "AGPL-3.0-only",
+                          "AGPL-3.0-or-later",
+                          "APL-1.0",
+                          "APSL-1.0",
+                          "APSL-1.1",
+                          "APSL-1.2",
+                          "APSL-2.0",
+                          "Apache-1.1",
+                          "Apache-2.0",
+                          "Artistic-1.0",
+                          "Artistic-1.0-Perl",
+                          "Artistic-1.0-cl8",
+                          "Artistic-2.0",
+                          "BSD-1-Clause",
+                          "BSD-2-Clause",
+                          "BSD-2-Clause-Patent",
+                          "BSD-3-Clause",
+                          "BSD-3-Clause-LBNL",
+                          "BSL-1.0",
+                          "CAL-1.0",
+                          "CAL-1.0-Combined-Work-Exception",
+                          "CATOSL-1.1",
+                          "CDDL-1.0",
+                          "CECILL-2.1",
+                          "CNRI-Python",
+                          "CPAL-1.0",
+                          "CPL-1.0",
+                          "CUA-OPL-1.0",
+                          "ECL-1.0",
+                          "ECL-2.0",
+                          "EFL-1.0",
+                          "EFL-2.0",
+                          "EPL-1.0",
+                          "EPL-2.0",
+                          "EUDatagrid",
+                          "EUPL-1.1",
+                          "EUPL-1.2",
+                          "Entessa",
+                          "Fair",
+                          "Frameworx-1.0",
+                          "GPL-2.0-only",
+                          "GPL-2.0-or-later",
+                          "GPL-3.0-only",
+                          "GPL-3.0-or-later",
+                          "HPND",
+                          "IPA",
+                          "IPL-1.0",
+                          "ISC",
+                          "Intel",
+                          "LGPL-2.0-only",
+                          "LGPL-2.0-or-later",
+                          "LGPL-2.1-only",
+                          "LGPL-2.1-or-later",
+                          "LGPL-3.0-only",
+                          "LGPL-3.0-or-later",
+                          "LPL-1.0",
+                          "LPL-1.02",
+                          "LPPL-1.3c",
+                          "LiLiQ-P-1.1",
+                          "LiLiQ-R-1.1",
+                          "LiLiQ-Rplus-1.1",
+                          "MIT",
+                          "MPL-1.0",
+                          "MPL-1.1",
+                          "MPL-2.0",
+                          "MPL-2.0-no-copyleft-exception",
+                          "MS-PL",
+                          "MS-RL",
+                          "MirOS",
+                          "Motosoto",
+                          "MulanPSL-2.0",
+                          "Multics",
+                          "NASA-1.3",
+                          "NCSA",
+                          "NGPL",
+                          "NPOSL-3.0",
+                          "NTP",
+                          "Naumen",
+                          "Nokia",
+                          "OCLC-2.0",
+                          "OFL-1.1",
+                          "OFL-1.1-RFN",
+                          "OFL-1.1-no-RFN",
+                          "OGTSL",
+                          "OSET-PL-2.1",
+                          "OSL-1.0",
+                          "OSL-2.0",
+                          "OSL-2.1",
+                          "OSL-3.0",
+                          "PHP-3.0",
+                          "PHP-3.01",
+                          "PostgreSQL",
+                          "Python-2.0",
+                          "QPL-1.0",
+                          "RPL-1.1",
+                          "RPL-1.5",
+                          "RPSL-1.0",
+                          "RSCPL",
+                          "SISSL",
+                          "SPL-1.0",
+                          "SimPL-2.0",
+                          "Sleepycat",
+                          "UCL-1.0",
+                          "UPL-1.0",
+                          "Unlicense",
+                          "VSL-1.0",
+                          "W3C",
+                          "Watcom-1.0",
+                          "Xnet",
+                          "ZPL-2.0",
+                          "Zlib"])
diff --git a/test/runtests.jl b/test/runtests.jl
@@ -58,7 +58,7 @@ dorian_gray = """
     There is no such thing as a moral or an immoral book.  Books are well
     written, or badly written.  That is all."""
 
-@testset "LicenseCheck.jl" begin
+@testset "`licensecheck`" begin
     result = licensecheck(MIT)
     @test result.licenses == ["MIT"]
     @test result.percent_covered ≈ 100.0 atol = 2
@@ -77,3 +77,8 @@ dorian_gray = """
           100 * (length(MIT) + length(Latex2e)) /
           (length(dorian_gray) + length(MIT) + length(Latex2e)) atol = 5
 end
+
+@testset "`is_osi_approved`" begin
+    @test is_osi_approved("MIT") == true
+    @test is_osi_approved("ABC") == false
+end