Allow readgbk to take an IOStream

README.md

@@ -5,19 +5,16 @@
 GenomicAnnotations is a package for reading, modifying, and writing genomic annotations in the GenBank format.
 
 ## Installation
+GenomicAnnotations depends on [BioSequences](https://github.com/BioJulia/BioSequences.jl), which is registered in [BioJuliaRegistry](https://github.com/BioJulia/BioJuliaRegistry). To install it you must first add the registry to Julia's package manager:
 ```julia
 julia>]
+pkg> registry add https://github.com/BioJulia/BioJuliaRegistry.git
 pkg> add GenomicAnnotations
 ```
-or
-```julia
-using Pkg
-Pkg.add("GenomicAnnotations")
-```
 
 
 ## Usage
-GenBank files are read with `readgbk(gbkfile)`, which returns a vector of `Chromosome`s. `gbkfile` can be gzipped as long as the filename ends in ".gz". If we're only interested in the first chromosome in `example.gbk` we only need to store the first element.
+GenBank files are read with `readgbk(input)`, which returns a vector of `Chromosome`s. `input` can be an `IOStream` or a file path. GZipped data can be read by setting the keyword `gunzip` to true, which is done automatically if a filename ending in ".gz" is passed as `input`. If we're only interested in the first chromosome in `example.gbk` we only need to store the first element.
 ```julia
 chr = readgbk("test/example.gbk")[1]
 ```

docs/src/index.md

@@ -5,19 +5,16 @@ GenomicAnnotations is a package for reading, modifying, and writing genomic anno
 
 
 ## Installation
+GenomicAnnotations depends on [BioSequences](https://github.com/BioJulia/BioSequences.jl), which is registered in [BioJuliaRegistry](https://github.com/BioJulia/BioJuliaRegistry). To install it you must first add the registry to Julia's package manager:
 ```julia
 julia>]
+pkg> registry add https://github.com/BioJulia/BioJuliaRegistry.git
 pkg> add GenomicAnnotations
 ```
-or
-```julia
-using Pkg
-Pkg.add("GenomicAnnotations")
-```
 
 
 ## Examples
-GenBank files are read with `readgbk(pathtofile)`, which returns a vector of `Chromosome`s. `gbkfile` can be gzipped as long as the filename ends in ".gz". If we're only interested in the first chromosome in `example.gbk` we only need to store the first element.
+GenBank files are read with `readgbk(input)`, which returns a vector of `Chromosome`s. `input` can be an `IOStream` or a file path. GZipped data can be read by setting the keyword `gunzip` to true, which is done automatically if a filename ending in ".gz" is passed as `input`. If we're only interested in the first chromosome in `example.gbk` we only need to store the first element.
 ```julia
 chr = readgbk("test/example.gbk")[1]
 ```

docs/src/io.md

@@ -1,7 +1,7 @@
 # I/O
 
 ## Input
-Annotation files are read with `readgbk(pathtofile)`. Currently this assumes that the file follows standard [GenBank format](http://www.insdc.org/files/feature_table.html#7.1.2).
+Annotation files are read with `readgbk(input)`. Currently this assumes that the file follows standard [GenBank format](http://www.insdc.org/files/feature_table.html#7.1.2).
 
 ```@docs
 readgbk(file)

src/readgbk.jl

@@ -175,28 +175,36 @@ end
 
 
 """
-    readgbk(filename)
+    readgbk(input, G::Type = Gene; gunzip = false)
 
-Parse GenBank-formatted file `filename`, returning a `Vector{Chromosome}`.
+Parse GenBank-formatted file, returning a `Vector{Chromosome}`. `input` can be a file path or an `IOStream`. File names ending in ".gz" are assumed to be gzipped and are decompressed. Setting `gunzip` to `true` forces this behaviour.
+The type of `AbstractGene` to be used can be specified with `G`, though currently the only option is `Gene`.
 """
-function readgbk(filename, G::Type = Gene)
+function readgbk(filename::AbstractString, G::Type = Gene; gunzip = false)
     gz = filename[end-2:end] == ".gz"
-    finished = false
-    chrs = Chromosome{G}[]
-    if gz
-        f = GZip.open(filename)
+    if gz || gunzip
+        GZip.open(f -> readgbk(f, G), filename)
     else
-        f = open(filename)
+        open(f -> readgbk(f, G), filename)
     end
-    lines = readlines(f)
-    currentline = 1
-    while !finished
-        if currentline >= length(lines)
-            break
-        end
-        i, chr = parsechromosome(lines[currentline:end], G)
-        currentline += i
-        push!(chrs, chr)
-    end
-    return chrs
+end
+
+function readgbk(input::IO, G::Type = Gene; gunzip = false)
+	finished = false
+	chrs = Chromosome{G}[]
+	if gunzip
+		lines = readlines(gzdopen(input))
+	else
+		lines = readlines(input)
+	end
+	currentline = 1
+	while !finished
+		if currentline >= length(lines)
+			break
+		end
+		i, chr = parsechromosome(lines[currentline:end], G)
+		currentline += i
+		push!(chrs, chr)
+	end
+	chrs
 end