Merge pull request #18 from jonathanBieler/develop

add empty! in read! method

Project.toml

@@ -29,6 +29,7 @@ BioSequences = "7e6ae17a-c86d-528c-b3b9-7f778a29fe59"
 Documenter = "e30172f5-a6a5-5a46-863b-614d45cd2de4"
 FormatSpecimens = "3372ea36-2a1a-11e9-3eb7-996970b6ffbd"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+CodecZlib = "944b1d66-785c-5afd-91f1-9de20f533193"
 
 [targets]
-test = ["BioSequences", "Documenter", "FormatSpecimens", "Test"]
+test = ["BioSequences", "Documenter", "FormatSpecimens", "Test", "CodecZlib"]

docs/src/man/gff3.md

@@ -49,7 +49,6 @@ record = GFF3.Record()
 
 # Iterate over records.
 while !eof(reader)
-    empty!(record)
     read!(reader, record)
     # do something
 end

src/reader.jl

@@ -110,6 +110,7 @@ function Base.close(reader::Reader)
 end
 
 function Base.read!(reader::Reader, record::Record)
+    empty!(record)
     return readrecord!(reader.state.stream, reader, record)
 end
 

test/runtests.jl

@@ -6,6 +6,7 @@ using BioGenerics
 using FASTX.FASTA
 using FormatSpecimens
 using GenomicFeatures
+using CodecZlib
 
 import BioSequences: @dna_str
 
@@ -74,9 +75,11 @@ import BioGenerics.Exceptions: MissingFieldException
         # in-place parsing
         stream = open(GFF3.Reader, filename)
         entry = eltype(stream)()
+        records = GFF3.Record[]
         while !eof(stream)
             try
                 read!(stream, entry)
+                push!(records, copy(entry))
             catch ex
                 if isa(ex, EOFError)
                     break
@@ -86,36 +89,67 @@ import BioGenerics.Exceptions: MissingFieldException
         close(stream)
 
         # copy
-        records = GFF3.Record[]
+        records2 = GFF3.Record[]
         reader = open(GFF3.Reader, filename)
         output = IOBuffer()
         writer = GFF3.Writer(output)
         for record in reader
             write(writer, record)
-            push!(records, record)
+            push!(records2, record)
         end
         close(reader)
         flush(writer)
 
-        records2 = GFF3.Record[]
+        records3 = GFF3.Record[]
         for record in GFF3.Reader(IOBuffer(take!(output)))
+            push!(records3, record)
+        end
+        return records == records2 == records3
+    end
+
+    function check_gff3_parse_gzip(filename)
+
+        # in-place parsing
+        stream = GFF3.Reader(GzipDecompressorStream(open(filename)))
+        record = GFF3.Record()
+        records = GFF3.Record[]
+        while !eof(stream)
+            read!(stream, record)
+            push!(records, copy(record))
+        end
+        close(stream)
+
+        # copy
+        records2 = GFF3.Record[]
+        reader = GFF3.Reader(GzipDecompressorStream(open(filename)))
+
+        output = IOBuffer()
+        writer = GFF3.Writer(output)
+        for record in reader
+            write(writer, record)
             push!(records2, record)
         end
-        return records == records2
+        close(reader)
+        flush(writer)
+
+        records3 = GFF3.Record[]
+        for record in GFF3.Reader(IOBuffer(take!(output)))
+            push!(records3, record)
+        end
+        return records == records2 == records3
     end
 
     dir_gff3 = path_of_format("GFF3")
 
     for specimen in list_valid_specimens("GFF3")
 
-        if hastag(specimen, "gzip")
-            # skip compressed files
-            continue
-        end
-
         filepath = joinpath(dir_gff3, filename(specimen))
 
-        @test check_gff3_parse(filepath)
+        if hastag(specimen, "gzip")
+            @test check_gff3_parse_gzip(filepath)
+        else
+            @test check_gff3_parse(filepath)
+        end
 
     end