Merge branch 'release/1.4.0'

.travis.yml

@@ -9,7 +9,6 @@ env:
 language: python
 
 python:
-  - "3.4"
   - "3.6"
 
 install:

CHANGES.md

@@ -1,11 +1,16 @@
 # CHANGES
 
+## 1.4.0
+
+* Correct base config for file types accepted.  File_2 should only accept `f(?:ast)q.gz` (upper/lower)
+* Only allow compresed fastq.
+
 ## 1.3.0
 
 * Fixes `valid_q` value of `seq-valid` json report.  Always returned false previously.
 * Correct command line help text for `seq-valid` input option.
-* Extends the `seq-valid` json report to include the ascii range detected and which types of
-phred score these align to.
+* Extends the `seq-valid` json report to include the ascii range detected and which types of phred
+  score these align to.
 * Additional command line options for `seq-valid`
   * `-o | --output` - Generates an interleaved gzip compressed fastq file when input is paired fastq
   * `-q | --qc` - Specify the number of pairs to be used when assessing the phred quality range

cgp_seq_input_val/config/IMPORT-1.0.json

@@ -36,8 +36,8 @@
                         {"value": "N"}]
     },
     "validate_ext": {
-      "File": [".fastq", ".fastq.gz", ".fq", ".fq.gz", ".bam", ".cram"],
-      "File_2": [".fastq", ".fastq.gz", ".fq", ".fq.gz", ".bam", ".cram"]
+      "File": [".fastq.gz", ".fq.gz", ".bam", ".cram"],
+      "File_2": [".fastq.gz", ".fq.gz"]
     }
   }
 }

cgp_seq_input_val/manifest.py

@@ -528,15 +528,18 @@ def file_ext_check(self, rules):
                     (base, ext) = os.path.splitext(base)
                 full_ext = ext + extra
 
-                if full_ext not in rules[f_type]:
-                    raise ValidationError("File extension of '%s' is not valid, \
-                                          '%s' on line %d"
-                                          % (full_ext, f_type, cnt))
+                if full_ext.lower() not in rules[f_type]:
+                    valid_extn = ', '.join(rules[f_type])
+                    raise ValidationError(
+                        f"File extension of '{full_ext}' is not valid ({valid_extn}), " +
+                        f"'{f_type}' on line {cnt} of manifest."
+                    )
 
                 if last_ext is not None and last_ext != full_ext:
-                    raise ValidationError("File extensions for same row must \
-                                          match, '%s' vs '%s' on line %d"
-                                          % (last_ext, full_ext, cnt))
+                    raise ValidationError(
+                        "File extensions for same row must match," +
+                        f"'{last_ext}' vs '{full_ext}' on line {cnt} of manifest."
+                    )
                 last_ext = full_ext
 
     def heading_check(self, config):

setup.py

@@ -9,8 +9,8 @@
     'url': 'https://github.com/cancerit/cgp_seq_input_val',
     'download_url': '',
     'author_email': '[email protected]',
-    'version': '1.3.0',
-    'python_requires': '>= 3.4',
+    'version': '1.4.0',
+    'python_requires': '>= 3.6',
     'setup_requires': ['pytest'],
     'install_requires': ['progressbar2', 'xlrd', 'xopen'],
     'packages': ['cgp_seq_input_val'],

tests/data/file_set_good/files_good.tsv

@@ -7,6 +7,6 @@ Seq Protocol:	WGS
 Data Type:	DNA
 Mark Duplicates:	Y
 Group_ID	Sample	Normal_Tissue	Group_Control	Library	File	File_2
-1	Bob	N	N	1	banana.fastq	gru.fastq
+1	Bob	N	N	1	banana.fastq.gz	gru.fastq.gz
 1	Stuart	Y	N	1	bello.bam
 1	Kevin	Y	Y	1	read1.fq.gz	read2.fq.gz

tests/data/with_uuid.tsv

@@ -7,6 +7,6 @@ Seq Protocol:	WGS
 Data Type:	DNA
 Mark Duplicates:	Y
 Group_ID	Sample	Normal_Tissue	Group_Control	Library	File	File_2
-1	Bob	N	N	1	banana.fastq	gru.fastq
+1	Bob	N	N	1	banana.fastq.gz	gru.fastq.gz
 1	Stuart	Y	N	1	bello.bam
 1	Kevin	Y	Y	1	read1.fq.gz	read2.fq.gz