fix outpudir issue with annotate; add pid to logfile to avoid collision

bin/funannotate-functional.py

@@ -349,7 +349,7 @@ def parseEggNoggMapper(input, output, GeneDict):
 
 #start here rest of script
 #create log file
-log_name = 'funannotate-annotate.log'
+log_name = 'funannotate-annotate.'+str(os.getpid())+'.log'
 if os.path.isfile(log_name):
     os.remove(log_name)
 
@@ -444,12 +444,14 @@ def parseEggNoggMapper(input, output, GeneDict):
         sys.exit(1)
     else:
         outputdir = args.out
-        #create outputdir and subdirs
-        if not os.path.isdir(outputdir):
-            os.makedirs(outputdir)
-            os.makedirs(os.path.join(outputdir, 'annotate_misc'))
-            os.makedirs(os.path.join(outputdir, 'annotate_results'))
-            os.makedirs(os.path.join(outputdir, 'logfiles')) 
+        if os.path.isdir(outputdir):
+            lib.log.error("Output directory %s already exists, will use any existing data.  If this is not what you want, exit, and provide a unique name for output folder" % (outputdir))
+        #create outputdir and subdirs if not already present
+        lib.createdir(outputdir)
+        lib.createdir(os.path.join(outputdir, 'annotate_misc'))
+        lib.createdir(os.path.join(outputdir, 'annotate_results'))
+        lib.createdir(os.path.join(outputdir, 'logfiles'))
+
     if not args.genbank:
         if not args.fasta or not args.gff:
             lib.log.error("You did not specifiy the apropriate input files, either: \n1) GenBank \n2) Genome FASTA + GFF3")
@@ -465,21 +467,7 @@ def parseEggNoggMapper(input, output, GeneDict):
                 prefix = args.rename.replace('_', '')
             lib.log.info("Parsing annotation and preparing annotation files.")
             GeneCounts = lib.convertgff2tbl(GFF, prefix, Scaffolds, Proteins, Transcripts, annotTBL)
-    else:
-        #create output directories
-        if not os.path.isdir(outputdir):
-            os.makedirs(outputdir)
-            os.makedirs(os.path.join(outputdir, 'annotate_misc'))
-            os.makedirs(os.path.join(outputdir, 'annotate_results'))
-            os.makedirs(os.path.join(outputdir, 'logfiles'))
-        else:
-            lib.log.error("Output directory %s already exists, will use any existing data.  If this is not what you want, exit, and provide a unique name for output folder" % (outputdir))
-            if not os.path.isdir(os.path.join(outputdir, 'annotate_misc')):
-                os.makedirs(os.path.join(outputdir, 'annotate_misc'))
-            if not os.path.isdir(os.path.join(outputdir, 'annotate_results')):
-                os.makedirs(os.path.join(outputdir, 'annotate_results'))
-            if not os.path.isdir(os.path.join(outputdir, 'logfiles')):
-                os.makedirs(os.path.join(outputdir, 'logfiles'))                
+    else:             
         genbank = args.genbank
         Scaffolds = os.path.join(outputdir, 'annotate_misc', 'genome.scaffolds.fasta')
         Proteins = os.path.join(outputdir, 'annotate_misc', 'genome.proteins.fasta')
@@ -1290,4 +1278,4 @@ def parseEggNoggMapper(input, output, GeneDict):
 if os.path.isfile(log_name):
     if not os.path.isdir(os.path.join(outputdir, 'logfiles')):
         os.makedirs(os.path.join(outputdir, 'logfiles'))
-    os.rename(log_name, os.path.join(outputdir, 'logfiles', log_name))
+    os.rename(log_name, os.path.join(outputdir, 'logfiles', 'funannotate-annotate.log'))

dockerbuild/Dockerfile-base

@@ -27,19 +27,18 @@ COPY repeatmodeler.txt \
 
 WORKDIR /home/linuxbrew
 
-RUN wget --quiet https://repo.continuum.io/miniconda/Miniconda2-latest-Linux-x86_64.sh -O ~/miniconda.sh && \
+RUN wget --quiet https://repo.continuum.io/miniconda/Miniconda2-4.6.14-Linux-x86_64.sh -O ~/miniconda.sh && \
     sudo /bin/bash ~/miniconda.sh -b -p /home/linuxbrew/conda &&  rm ~/miniconda.sh && sudo chown -R linuxbrew: /home/linuxbrew/conda && \
-    conda update -y conda && conda config --add channels r && conda config --add channels defaults && \
-    conda config --add channels etetoolkit && conda config --add channels conda-forge && conda config --add channels bioconda && \
-    conda install -y numpy pandas scipy matplotlib seaborn natsort scikit-learn psutil biopython requests snap glimmerhmm=3.0.4=pl526h0a44026_3 \
-    goatools fisher bedtools blat hmmer exonerate diamond tbl2asn hisat2 ucsc-pslcdnafilter stringtie perl-dbd-sqlite \
-    samtools raxml trimal mafft phyml kallisto bowtie2 infernal perl-threaded perl-db-file perl-bioperl perl-dbd-mysql \
+    conda config --add channels r && conda config --add channels defaults && \
+    conda config --add channels etetoolkit && conda config --add channels bioconda && conda config --add channels conda-forge && \
+    conda install -y numpy pandas scipy matplotlib seaborn natsort scikit-learn psutil biopython requests snap glimmerhmm \
+    goatools fisher bedtools blat hmmer exonerate diamond tbl2asn hisat2 ucsc-pslcdnafilter stringtie perl-dbd-sqlite perl-json \
+    samtools raxml trimal mafft phyml kallisto bowtie2 infernal perl-threaded perl-db-file perl-bioperl perl-dbd-mysql perl-clone \
     perl-app-cpanminus mummer ete3 ete_toolchain minimap2 salmon=0.9.1 jellyfish htslib nano perl-text-soundex perl-scalar-util-numeric && \
     conda clean --all && \
     sudo ln -s /home/linuxbrew/conda/bin/ete3_apps/bin/raxmlHPC-PTHREADS-SSE3 /home/linuxbrew/conda/bin/ete3_apps/bin/raxmlHPC-PTHREADS && \
-    cpanm Getopt::Long Pod::Usage File::Basename \
-    Thread::Queue Carp Data::Dumper YAML Hash::Merge Logger::Simple Parallel::ForkManager \
-    DBI Clone JSON LWP::UserAgent && \
+    cpanm Getopt::Long Pod::Usage File::Basename Thread::Queue Carp Data::Dumper \
+    YAML Hash::Merge Logger::Simple Parallel::ForkManager DBI LWP::UserAgent && \
     wget https://sourceforge.net/projects/codingquarry/files/CodingQuarry_v2.0.tar.gz && \
     tar -zxvf CodingQuarry_v2.0.tar.gz && rm CodingQuarry_v2.0.tar.gz && cd CodingQuarry_v2.0 && make && cd /home/linuxbrew/ && \
     wget --no-check-certificate https://tandem.bu.edu/trf/downloads/trf409.linux64 && \

lib/library.py

@@ -1,5 +1,6 @@
 from __future__ import division
 import os, subprocess, logging, sys, argparse, inspect, csv, time, re, shutil, datetime, platform, multiprocessing, itertools, hashlib, math, types, gzip, operator, textwrap
+import errno
 from natsort import natsorted
 from lib.interlap import InterLap
 from collections import defaultdict
@@ -251,42 +252,50 @@ class colr:
     WARN = '\033[93m'
 
 class gzopen(object):
-   """Generic opener that decompresses gzipped files
-   if needed. Encapsulates an open file or a GzipFile.
-   Use the same way you would use 'open()'.
-   """
-   def __init__(self, fname):
-      f = open(fname)
-      # Read magic number (the first 2 bytes) and rewind.
-      magic_number = f.read(2)
-      f.seek(0)
-      # Encapsulated 'self.f' is a file or a GzipFile.
-      if magic_number == '\x1f\x8b':
-         self.f = gzip.GzipFile(fileobj=f)
-      else:
-         self.f = f
-
-   # Define '__enter__' and '__exit__' to use in
-   # 'with' blocks. Always close the file and the
-   # GzipFile if applicable.
-   def __enter__(self):
-      return self
-   def __exit__(self, type, value, traceback):
-      try:
-         self.f.fileobj.close()
-      except AttributeError:
-         pass
-      finally:
-         self.f.close()
-
-   # Reproduce the interface of an open file
-   # by encapsulation.
-   def __getattr__(self, name):
-      return getattr(self.f, name)
-   def __iter__(self):
-      return iter(self.f)
-   def next(self):
-      return next(self.f)
+    """Generic opener that decompresses gzipped files
+    if needed. Encapsulates an open file or a GzipFile.
+    Use the same way you would use 'open()'.
+    """
+    def __init__(self, fname):
+        f = open(fname)
+        # Read magic number (the first 2 bytes) and rewind.
+        magic_number = f.read(2)
+        f.seek(0)
+        # Encapsulated 'self.f' is a file or a GzipFile.
+        if magic_number == '\x1f\x8b':
+            self.f = gzip.GzipFile(fileobj=f)
+        else:
+            self.f = f
+
+    # Define '__enter__' and '__exit__' to use in
+    # 'with' blocks. Always close the file and the
+    # GzipFile if applicable.
+    def __enter__(self):
+        return self
+    def __exit__(self, type, value, traceback):
+        try:
+            self.f.fileobj.close()
+        except AttributeError:
+            pass
+        finally:
+            self.f.close()
+
+    # Reproduce the interface of an open file
+    # by encapsulation.
+    def __getattr__(self, name):
+        return getattr(self.f, name)
+    def __iter__(self):
+        return iter(self.f)
+    def next(self):
+        return next(self.f)
+
+def createdir(name):
+	try:
+		os.makedirs(name)
+	except OSError as exc:
+		if exc.errno != errno.EEXIST:
+			raise
+		pass
 
 def softwrap2(input):
     return textwrap.fill(input, width=80)