Get synonyms (#30)

Fetch alternative names for the same substance

Ref: https://pubchem.ncbi.nlm.nih.gov/docs/pug-rest\#section\=Synonyms

---------

Co-authored-by: Filipe Chichorro <[email protected]>

Author: tp2750

docs/src/index.md

@@ -108,6 +108,7 @@ query_substructure_pug
 query_substructure
 get_for_cids
 pug
+get_synonyms
 ```
 
 ### Utilities

src/PubChemCrawler.jl

@@ -3,7 +3,7 @@ module PubChemCrawler
 using HTTP
 using LightXML
 
-export atomregex, parse_formula, get_cid, get_cids, get_for_cids, query_substructure, query_substructure_pug, pug
+export atomregex, parse_formula, get_cid, get_cids, get_for_cids, query_substructure, query_substructure_pug, pug, get_synonyms
 
 include("utils.jl")
 include("query.jl")

src/query.jl

@@ -261,3 +261,30 @@ function pug(args...; silent = true, escape_args = true, return_text = false, st
     b = return_text ? chomp(String(r.body)) : r.body
     return b
 end
+
+"""
+    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