switch PDB downloads from ftp to https

Author: jgreener64

src/download.jl

@@ -9,6 +9,8 @@ export
     downloadallobsoletepdb,
     retrievepdb
 
+const pdb_download_prefix = "https://files.wwpdb.org/pub/pdb"
+
 """
     pdbentrylist()
 
@@ -21,7 +23,7 @@ function pdbentrylist()
     @info "Fetching the list of all PDB entries from the RCSB server"
     tempfilepath = tempname()
     try
-        Downloads.download("ftp://ftp.wwpdb.org/pub/pdb/derived_data/index/entries.idx", tempfilepath)
+        Downloads.download("$pdb_download_prefix/derived_data/index/entries.idx", tempfilepath)
         open(tempfilepath) do input
             reading = false
             for line in eachline(input)
@@ -53,7 +55,7 @@ end
 Obtain the list of Protein Data Bank (PDB) entries from a RCSB weekly status
 file by specifying its URL.
 
-An example URL is ftp://ftp.wwpdb.org/pub/pdb/data/status/latest/added.pdb.
+An example URL is $pdb_download_prefix/pub/pdb/data/status/latest/added.pdb.
 Requires an internet connection.
 """
 function pdbstatuslist(url::AbstractString)
@@ -92,9 +94,9 @@ Obtain three lists giving the added, modified and obsolete Protein Data Bank
 Requires an internet connection.
 """
 function pdbrecentchanges()
-    addedlist = pdbstatuslist("ftp://ftp.wwpdb.org/pub/pdb/data/status/latest/added.pdb")
-    modifiedlist = pdbstatuslist("ftp://ftp.wwpdb.org/pub/pdb/data/status/latest/modified.pdb")
-    obsoletelist = pdbstatuslist("ftp://ftp.wwpdb.org/pub/pdb/data/status/latest/obsolete.pdb")
+    addedlist = pdbstatuslist("$pdb_download_prefix/data/status/latest/added.pdb")
+    modifiedlist = pdbstatuslist("$pdb_download_prefix/data/status/latest/modified.pdb")
+    obsoletelist = pdbstatuslist("$pdb_download_prefix/data/status/latest/obsolete.pdb")
     return addedlist, modifiedlist, obsoletelist
 end
 
@@ -111,7 +113,7 @@ function pdbobsoletelist()
     @info "Fetching the list of all obsolete PDB entries from the RCSB server"
     tempfilepath = tempname()
     try
-        Downloads.download("ftp://ftp.wwpdb.org/pub/pdb/data/status/obsolete.dat", tempfilepath)
+        Downloads.download("$pdb_download_prefix/data/status/obsolete.dat", tempfilepath)
         open(tempfilepath) do input
             for line in eachline(input)
                 # Check if its an obsolete pdb entry and not headers

test/Project.toml

@@ -6,6 +6,7 @@ BioSequences = "7e6ae17a-c86d-528c-b3b9-7f778a29fe59"
 CodecZlib = "944b1d66-785c-5afd-91f1-9de20f533193"
 DSSP_jll = "74334e00-59ce-546d-b517-81f3b7e1d491"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
+Downloads = "f43a241f-c20a-4ad4-852c-f6b1247861c6"
 Format = "1fa38f19-a742-5d3f-a2b9-30dd87b9d5f8"
 Graphs = "86223c79-3864-5bf0-83f7-82e725a168b6"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"

test/runtests.jl

@@ -14,6 +14,7 @@ using MetaGraphs
 using RecipesBase
 using STRIDE_jll
 
+using Downloads
 using LinearAlgebra
 using Test
 
@@ -49,7 +50,8 @@ using BioStructures:
     tokenizecifstructure,
     formatmmcifcol,
     requiresnewline,
-    requiresquote
+    requiresquote,
+    pdb_download_prefix
 
 # Get the path to BioFmtSpecimens and download it if required
 fmtdir = BioCore.Testing.get_bio_fmt_specimens("master", false)
@@ -90,12 +92,9 @@ Aqua.test_all(BioStructures; ambiguities=(recursive=false))
     @test length(pdbentrylist()) > 100000
 
     # This may be empty on a given date so we just check it has the correct type
-    @test isa(pdbstatuslist("ftp://ftp.wwpdb.org/pub/pdb/data/status/latest/added.pdb"), Vector{String})
+    @test isa(pdbstatuslist("$pdb_download_prefix/data/status/latest/added.pdb"), Vector{String})
     # Invalid URL
-    # The error type changes from ErrorException to ProcessFailedException in Julia v1.2
-    #   therefore we check for the more general Exception type
-    # This also applies to two examples below
-    @test_throws Exception pdbstatuslist("ftp://ftp.wwpdb.org/pub/pdb/data/status/latest/dummy.pdb")
+    @test_throws RequestError pdbstatuslist("$pdb_download_prefix/data/status/latest/dummy.pdb")
 
     addedlist, modifiedlist, obsoletelist = pdbrecentchanges()
 
@@ -104,13 +103,13 @@ Aqua.test_all(BioStructures; ambiguities=(recursive=false))
     # Invalid PDB ID format
     @test_throws ArgumentError downloadpdb("1a df")
     # Valid PDB ID format but PDB does not exist
-    @test_throws Exception downloadpdb("no1e", dir=temp_dir)
+    @test_throws RequestError downloadpdb("no1e", dir=temp_dir)
     # Invalid file format
     @test_throws TypeError downloadpdb("1alw", dir=temp_dir, format=String)
     # Biological assembly not available in PDBXML and MMTF
     @test_throws ArgumentError downloadpdb("1alw", dir=temp_dir, format=PDBXMLFormat, ba_number=1)
     # Invalid BA number for this PDB entry
-    @test_throws Exception downloadpdb("1alw", dir=temp_dir, format=MMCIFFormat, ba_number=10)
+    @test_throws RequestError downloadpdb("1alw", dir=temp_dir, format=MMCIFFormat, ba_number=10)
     # Test if downloadpdb returns the path to the downloaded file
     @test isfile(downloadpdb("1crn", dir=temp_dir))