Merge pull request NAL-i5K#43 from NAL-i5K/add_appveyor

Add appveyor

.appveyor.yml

@@ -0,0 +1,40 @@
+image:
+    - Visual Studio 2013
+    - Visual Studio 2015
+    - Visual Studio 2017
+
+environment:
+  matrix:
+    - PYTHON: C:\Python27-x64
+
+
+# scripts that are called at very beginning, before repo cloning
+init:
+  - git config --global core.autocrlf input
+
+# clone directory
+clone_folder: c:\projects\GFF3toolkit
+
+platform: x64
+
+configuration: Release
+
+services:
+  - postgresql96
+
+install:
+  - cd c:\projects\GFF3toolkit
+  - pip install .
+
+build: off
+
+test_script:
+  - gff3_QC -g example_file/example.gff3 -f example_file/reference.fa -o error.txt
+  - gff3_fix -qc_r error.txt -g example_file/example.gff3 -og corrected.gff3
+  - gff3_merge -g1 example_file/new_models.gff3 -g2 example_file/reference.gff3 -f example_file/reference.fa -og merged.gff -r merged_report.txt
+  - gff3_merge -g1 example_file/new_models_w_replace.gff3 -g2 example_file/reference.gff3 -f example_file/reference.fa -og merged.gff -r merged_report.txt -noAuto
+  - gff3_sort -g example_file/example.gff3 -og example-sorted.gff3
+  - ps: Write-Host "Test scripts are finished ..."
+
+deploy: false
+

README.md

@@ -1,6 +1,7 @@
 # GFF3toolkit - Python programs for processing GFF3 files
 
 [![Build Status](https://travis-ci.org/NAL-i5K/GFF3toolkit.svg?branch=master)](https://travis-ci.org/NAL-i5K/GFF3toolkit)
+[![Build status](https://ci.appveyor.com/api/projects/status/0do5uwu5je0gag1u?svg=true)](https://ci.appveyor.com/project/hsiaoyi0504/gff3toolkit)
 
 ## Background
 

gff3tool/lib/ERROR/ERROR.py

@@ -6,16 +6,11 @@
 # the Free Software Foundation; either version 3 of the License, or
 # (at your option) any later version.
 
-import sys
+
 # try to import from project first
-from os.path import dirname
-if dirname(__file__) == '':
-    lib_path = '../lib'
-else:
-    lib_path = dirname(__file__) + '/../lib'
-sys.path.insert(1, lib_path)
+from gff3tool.bin import version
 
-__version__ = '0.0.1'
+__version__ = version.__version__
 
 INFO = {
     'Ema0001': 'Parent feature start and end coordinates exceed those of child features',

gff3tool/lib/auto_assignment/create_annotation_summaries_nov21-7.pl

@@ -47,13 +47,15 @@
 
 open FI, "$transcript_type" or die "[Error] Cannot open $transcript_type.";
 while (<FI>){
-        chomp $_;        
+        chomp $_;
+		$_ =~ s/\R//g;
         $trans_type{$_} = $_;
-} 
-close FI;    
+}
+close FI;
 
 while ( my $line = <$GFF> ){
     chomp $line;
+	$line =~ s/\R//g;
 #ignore commented lines
     if ( $line =~ /^#/ ){
 	next;
@@ -71,7 +73,7 @@
 	my $stop = $array[4];
 	my $id = "NA";
 	my $owner = "NA";
-	my $name= "NA"; 
+	my $name= "NA";
 	my $symbol="NA";
 	my $mod_date="NA";
 	my $comments="NA";
@@ -109,7 +111,7 @@
 	}
 #populate gene/pseudogene  hash
 	if ( $array[2] =~ /gene|pseudogene/ ){
-#in gene hash, key: id; value: name, SO type, date modified, notes.	    
+#in gene hash, key: id; value: name, SO type, date modified, notes.
 	    $gene_ids{$id} = "$name\t$id\t$array[2]\t$mod_date\t$comments\t$replace\t$status";
 	}
 #populate transcript hash
@@ -121,13 +123,13 @@
 	    elsif ($parent eq "NA" ){
 	        $gene_ids{$parent} = "NA\tNA\tNA\tNA\tNA\tNA\tNA";
             my $link = "https://apollo.nal.usda.gov/".$species_code."/jbrowse/?loc=".$scaffold."%3A".$start."..".$stop."&tracks=DNA%2CAnnotations%2C".$species_code."_current_models&highlight=";
-                $transcript_ids{$id} = "$gene_ids{$parent}\t$owner\t$scaffold\t$start\t$stop\t$strand\t$array[2]\t$name\t$id\t$comments\t$replace\t$status\t$link";        
+                $transcript_ids{$id} = "$gene_ids{$parent}\t$owner\t$scaffold\t$start\t$stop\t$strand\t$array[2]\t$name\t$id\t$comments\t$replace\t$status\t$link";
         }
 	    else {
 		warn "parents and children out of synch here:\n$parent\t$id\n";
 	    }
 	}
-#populate transcript_ids hash w sequence mods (top-level, no parents, no children)	
+#populate transcript_ids hash w sequence mods (top-level, no parents, no children)
 	elsif ( $array[2] =~ /deletion|insertion|substitution|transposable_element/ ){
 	    my $link = "https://apollo.nal.usda.gov/".$species_code."/jbrowse/?loc=".$scaffold."%3A".$start."..".$stop."&tracks=DNA%2CAnnotations%2C".$species_code."_current_models&highlight=";
 	    $transcript_ids{$id} = "NA\t$name\t$array[2]\t$mod_date\tNA\tNA\tNA\t$owner\t$scaffold\t$start\t$stop\t$strand\t$array[2]\tNA\t$id\tNA\tNA\tNA\t$link";
@@ -170,7 +172,7 @@
 		    $CDS_phase{$parent}{$stop} = $array[7];
 		}
 	    }
-#already pre-populate true stop coordinate hash for proper aa length calculaton (accounting for stop codons; complete value in next section. id -> scaf  -> dir -> stop                                                                         
+#already pre-populate true stop coordinate hash for proper aa length calculaton (accounting for stop codons; complete value in next section. id -> scaf  -> dir -> stop
 	    $cds_true_stop_coordinate{$parent}{$scaffold}{$array[6]} = 1;
 	}
 	elsif ( $array[2] =~ /exon/ ){
@@ -187,8 +189,8 @@
     }
 }
 
-#will have to slice out string from last 3 bases of CDS (note that this is specific to Web Apollo coding - not all gff3s code their stop codons as CDS) and see whether it matches stop codons (or their reverse complement, depending on strand)         
-#TAG, TAA, TGA                                                                                                              
+#will have to slice out string from last 3 bases of CDS (note that this is specific to Web Apollo coding - not all gff3s code their stop codons as CDS) and see whether it matches stop codons (or their reverse complement, depending on strand)
+#TAG, TAA, TGA
 close $GFF;
 
 
@@ -197,6 +199,7 @@
 my $defline;
 while ( my $fline = <$FASTA> ){
     chomp $fline;
+	$fline =~ s/\R//g;
     if ( $fline =~ /^>(\S+)/ ){
 	$defline = $1;
     }
@@ -205,14 +208,14 @@
     }
 }
 
-#id -> scaf -> dir -> 1 (should be populated with true stop coordinate  
+#id -> scaf -> dir -> 1 (should be populated with true stop coordinate
 #code to determine whether stop codon is present in CDS and calculate true aa sequence length
 #WIP: STILL NO CODE TO INCORPORATE PHASE
 foreach my $cds ( keys %cds_true_stop_coordinate ){
     foreach my $scafkey ( keys %{$cds_true_stop_coordinate{$cds}} ){
 	if ( defined $fasta{$scafkey} ){
 	    foreach my $dirkey ( keys %{$cds_true_stop_coordinate{$cds}{$scafkey}} ){
-		if ( $dirkey eq "+" ){		    
+		if ( $dirkey eq "+" ){
 		    #for forward strand, stop coordinate in CDS_stop is true stop coordinate, and coordinate in CDS_start is true start coordinate
 		    my $forward_stop = $CDS_stop{$cds};
 		    my $stop_slice = substr( $fasta{$scafkey}, ($forward_stop -3), 3);
@@ -278,7 +281,7 @@
     if ( defined $num_exon_introns{$key} ){
 #if it has CDS
 	if ( defined $aas{$key} and defined $CDS_start{$key} and defined $CDS_stop{$key} ){
-#if it has a readthrough stop codon	    
+#if it has a readthrough stop codon
 	    if ( defined $stop_codon_readthrough{$key} ){
 		print $OUT "$transcript_ids{$key}\t$aas{$key}\t$CDS_start{$key}\t$CDS_stop{$key}\t$num_cds_introns{$key}\t$num_exon_introns{$key}\thas_readthrough_stop_codon\n";
 	    }
@@ -291,7 +294,7 @@
 	    print $OUT "$transcript_ids{$key}\tNA\tNA\tNA\tNA\tNA\tNA\t$num_exon_introns{$key}\tNA\n";
 	}
     }
-#if it doesn't have exons    
+#if it doesn't have exons
     else {
 	print $OUT "$transcript_ids{$key}\tNA\tNA\tNA\tNA\tNA\tNA\tNA\tNA\n";
     }

gff3tool/lib/auto_assignment/find_match.pl

@@ -25,15 +25,17 @@
 open FI, "$transcript_type" or die "[Error] Cannot open $transcript_type.";
 while (<FI>){
         chomp $_;
+		$_ =~ s/\R//g;
         $trans_type{$_} = $_;
-} 
-close FI;     
-   
+}
+close FI;
+
 print "Reading the gff file: $gff...\n";
 open FI, "$gff" or die "[Error] Cannot open $gff.";
 while (<FI>){
 	$line++;
 	chomp $_;
+	$_ =~ s/\R//g;
 	if ($_ =~ /^#/){next;}
 	my @t = split("\t", $_);
         if ($#t != 8){next;}
@@ -134,6 +136,7 @@
 open FI, "$blast" or die "[Error] Cannot open $blast.";
 while (<FI>){
 	chomp $_;
+	$_ =~ s/\R//g;
 	if ($_ =~ /^$/){ print "blast result is empty..."; exit; } # Check whether the blast result is epmpty...
 	my @t = split("\t", $_);
 	$#t!=11 and next;
@@ -144,7 +147,7 @@
     }elsif ($t[0] =~ /\|Parent=(.+?)\|ID=(.+?)\|/ or $t[0] =~ /\|Parent=(.+?)\|ID=(.+?)$/){
 		($qpar, $qid) = ($1, $2);
 	}
-	
+
 
     if ($t[1] !~ /Parent/){
         $t[1] =~ /ID=(.+?)\|/;
@@ -209,15 +212,15 @@
 foreach my $e (sort keys %diffparent){
 	my @pid = split("\t", $diffparent{$e}->{PAR});
 	my @t = split("\t", $diffparent{$e}->{BEST});
-	$t[0] =~ /(.+?):(\d+)\.\.(\d+):(.)\|/;	
-	my ($scaf1, $s1, $e1, $d1) = ($1, $2, $3, $4);	
-	$t[1] =~ /(.+?):(\d+)\.\.(\d+):(.)\|/;	
+	$t[0] =~ /(.+?):(\d+)\.\.(\d+):(.)\|/;
+	my ($scaf1, $s1, $e1, $d1) = ($1, $2, $3, $4);
+	$t[1] =~ /(.+?):(\d+)\.\.(\d+):(.)\|/;
 	my ($scaf2, $s2, $e2, $d2) = ($1, $2, $3, $4);
 
 	if ( !defined $gene2url{$pid[0]} ){
 	    $gene2url{$pid[0]} = 'Unassigned';
     }
-    
+
 
 	if ($scaf1 eq $scaf2 && $d1 eq $d2){
 		if (($s1 >= $s2 && $s1 <= $e2) || ($s2 >= $s1 && $s2 <= $e1)){

gff3tool/lib/auto_assignment/gen_spreadsheet.pl

@@ -15,6 +15,7 @@
 my $head = <FI>;
 while (<FI>){
 	chomp $_;
+	$_ =~ s/\R//g;
 	my @t = split("\t", $_);
 	if (defined $hit{$t[2]}){
 		$hit{$t[2]} .= ",$t[5]";
@@ -29,6 +30,7 @@
 $head = <FI>;
 while (<FI>){
 	chomp $_;
+	$_ =~ s/\R//g;
 	my @t = split("\t", $_);
 	if (defined $hit2{$t[2]}){
 		$hit2{$t[2]} .= ",$t[5]";
@@ -57,6 +59,8 @@
 	}
 }
 while (<FI>){
+	chomp $_;
+	$_ =~ s/\R//g;
 	my @t = split("\t", $_);
 	chomp @t;
 	my @info = ();

gff3tool/lib/check_gene_parent/find_wrongly_split_gene_parent.pl

@@ -23,7 +23,7 @@
 while (<FI>){
 	$line++;
 	chomp $_;
-        $_ =~ s/\R//g;
+    $_ =~ s/\R//g;
 	if ( $_ =~ /^##FASTA/ ){last;}#go to end of file if there's a FASTA section in the gff3 file
         elsif ($_ =~ /^#/){next;}
 	my @t = split("\t", $_);
@@ -101,6 +101,7 @@
 open FI, "$blast" or die "[Error] Cannot open $blast.";
 while (<FI>){
 	chomp $_;
+	$_ =~ s/\R//g;
 	if ($_ =~ /^$/){ print "blast result is empty..."; exit; } # Check whether the blast result is epmpty...
 	my @t = split("\t", $_);
 	$#t!=11 and next;

gff3tool/lib/function4gff/function4gff.py

@@ -6,13 +6,6 @@
 QC functions for processing multiple features between models (inter-model) in GFF3 file.
 """
 from __future__ import print_function
-
-#from collections import OrderedDict # not available in 2.6
-from itertools import groupby
-try:
-    from urllib import quote, unquote
-except ImportError:
-    from urllib.parse import quote, unquote
 import sys
 import re
 import logging
@@ -25,14 +18,9 @@
     lh = logging.StreamHandler()
     lh.setFormatter(logging.Formatter('%(levelname)-8s %(message)s'))
     logger.addHandler(lh)
-from os.path import dirname
-if dirname(__file__) == '':
-    lib_path = '../../lib'
-else:
-    lib_path = dirname(__file__) + '/../../lib'
-sys.path.insert(1, lib_path)
+from gff3tool.bin import version
 
-__version__ = '0.0.1'
+__version__ = version.__version__
 
 def randomID(size=32, chars=string.ascii_uppercase + string.digits):
     return ''.join(random.choice(chars) for _ in range(size))