JuliaHealth · fchichorro · Jul 8, 2023 · Jul 7, 2023 · Jul 8, 2023 · Jul 8, 2023
diff --git a/Project.toml b/Project.toml
@@ -8,7 +8,7 @@ HTTP = "cd3eb016-35fb-5094-929b-558a96fad6f3"
 LightXML = "9c8b4983-aa76-5018-a973-4c85ecc9e179"
 
 [compat]
-HTTP = "0.8, 0.9"
+HTTP = "0.8, 0.9, 1.9.8"
 LightXML = "0.8, 0.9"
 julia = "1"
 

diff --git a/src/PubChemCrawler.jl b/src/PubChemCrawler.jl
@@ -3,7 +3,7 @@ module PubChemCrawler
 using HTTP
 using LightXML
 
-export atomregex, parse_formula, get_cid, get_for_cids, query_substructure, query_substructure_pug
+export atomregex, parse_formula, get_cid, get_for_cids, query_substructure, query_substructure_pug, get_synonyms
 
 include("utils.jl")
 include("query.jl")

diff --git a/src/query.jl b/src/query.jl
@@ -172,3 +172,31 @@ function get_for_cids(cids;
 end
 
 get_for_cids(cid::Int; kwargs...) = get_for_cids([cid]; kwargs...)
+
+
+"""
+    synonyms = get_synonyms(name="glucose")
+    synonyms = get_synonyms(smiles="C([C@@H]1[C@H]([C@@H]([C@H](C(O1)O)O)O)O)O")
+    synonyms = get_synonyms(cid=5793)
+
+Return a list of substance or compound synonyms.
+"""
+function get_synonyms(; name=nothing, cid=nothing, smiles=nothing,
+         kwargs...)::Vector{String}
+    # inputs
+    input = "compound/"
+    if name !== nothing
+        (smiles === nothing && cid === nothing) || throw(ArgumentError("only one of name, cid, or smiles can be specified"))
+        input *= "name/$(HTTP.escapeuri(name))/"
+    elseif cid !== nothing
+        (smiles === nothing) || throw(ArgumentError("only one of name, cid, or smiles can be specified"))
+        input *= "cid/$cid/"
+    elseif smiles !== nothing
+        input *= "smiles/$smiles/"
+    else
+        throw(ArgumentError("one of name, cid, or smiles must be specified"))
+    end
+    url = prolog * input * "synonyms/TXT"
+    r = HTTP.request("GET", url; kwargs...)
+    return split(chomp(String(r.body)), "\n")
+end
diff --git a/test/http_record/CAS_as_json.bson b/test/http_record/CAS_as_json.bson
diff --git a/test/http_record/CAS_as_txt.bson b/test/http_record/CAS_as_txt.bson
diff --git a/test/http_record/aspirin_cid_from_name.bson b/test/http_record/aspirin_cid_from_name.bson
diff --git a/test/http_record/aspirin_cid_from_smiles.bson b/test/http_record/aspirin_cid_from_smiles.bson
diff --git a/test/http_record/aspirin_smiles_from_cid.bson b/test/http_record/aspirin_smiles_from_cid.bson
diff --git a/test/http_record/asprin_sdf_3d.bson b/test/http_record/asprin_sdf_3d.bson
diff --git a/test/http_record/cGMP_cid.bson b/test/http_record/cGMP_cid.bson
diff --git a/test/http_record/estriol_cid.bson b/test/http_record/estriol_cid.bson
diff --git a/test/http_record/estriol_substructure.bson b/test/http_record/estriol_substructure.bson
diff --git a/test/http_record/estriol_substructure_formulas.bson b/test/http_record/estriol_substructure_formulas.bson
diff --git a/test/http_record/estriol_synonyms_from_cid.bson b/test/http_record/estriol_synonyms_from_cid.bson
diff --git a/test/http_record/estriol_synonyms_from_name.bson b/test/http_record/estriol_synonyms_from_name.bson
diff --git a/test/http_record/estriol_synonyms_from_smiles.bson b/test/http_record/estriol_synonyms_from_smiles.bson
diff --git a/test/http_record/smarts.bson b/test/http_record/smarts.bson
diff --git a/test/http_record/smarts_pug.bson b/test/http_record/smarts_pug.bson
diff --git a/test/http_record/sodium_acetate_parent.bson b/test/http_record/sodium_acetate_parent.bson
diff --git a/test/runtests.jl b/test/runtests.jl
@@ -22,7 +22,10 @@ const allrecordings = [joinpath("http_record", file) for file in [
     "cGMP_cid.bson",
     "aspirin_cid_from_name.bson",
     "CAS_as_json.bson",
-    "CAS_as_txt.bson"
+    "CAS_as_txt.bson",
+    "estriol_synonyms_from_name.bson",
+    "estriol_synonyms_from_cid.bson",
+    "estriol_synonyms_from_smiles.bson"
 ]]
 const get_recordings = !all(isfile, allrecordings)
 
@@ -46,11 +49,11 @@ BrokenRecord.configure!(; path="http_record")
     @test 27125 ∈ df.CID   # check that estetrol has estriol as a substructure
     sleep(2.0 * get_recordings)
     df13 = CSV.File(playback(() -> query_substructure(;smarts="[r13]Br", output="CSV"), "smarts.bson")) |> DataFrame  # brominated 13-atom ring structures
-    @test 153064026 ∈ df13.CID
+    @test 118303825 ∈ df13.CID
     # The recommended approach for substructure searches is `query_substructure_pug`
     sleep(5.0 * get_recordings)
     cids13 = playback(() -> query_substructure_pug(;smarts="[r13]Br", poll_interval=10*get_recordings), "smarts_pug.bson")  # brominated 13-atom ring structures, via PUG interface
-    @test 153064026 ∈ cids13
+    @test 118303825 ∈ cids13
 
     # properties
     sleep(5.0 * get_recordings)
@@ -84,4 +87,11 @@ BrokenRecord.configure!(; path="http_record")
     @test dct[:InformationList][:Information][1][:RN] == ["40732-48-7", "7665-99-8"]
     sleep(5.0 * get_recordings)
     @test chomp(String(playback(() -> get_for_cids(cids[1]; xrefs="RN,", output="TXT"), "CAS_as_txt.bson"))) == "40732-48-7\n7665-99-8"
+
+    #synonyms
+    @test "Trimesta" ∈ playback(() -> get_synonyms(name="estriol"), "estriol_synonyms_from_name.bson")
+    sleep(5.0 * get_recordings)
+    @test "Trimesta" ∈ playback(() -> get_synonyms(cid=cid_estriol), "estriol_synonyms_from_cid.bson")
+    sleep(5.0 * get_recordings)
+    @test "Trimesta" ∈ playback(() -> get_synonyms(smiles="C[C@]12CC[C@H]3[C@H]([C@@H]1C[C@H]([C@@H]2O)O)CCC4=C3C=CC(=C4)O"), "estriol_synonyms_from_smiles.bson")
 end