Fixed stdout output

versions of python

python/obitools3/commands/ngsfilter.pyx

@@ -24,6 +24,9 @@ from cpython.exc cimport PyErr_CheckSignals
 from io import BufferedWriter
 
 
+MAX_PAT_LEN = 31
+
+
 __title__="Assign sequence records to the corresponding experiment/sample based on DNA tags and primers"
 
 
@@ -84,6 +87,8 @@ class Primer:
         @type direct:
         '''
         
+        assert len(sequence) <= MAX_PAT_LEN, "Primer %s is too long, 31 bp max" % sequence
+        
         assert sequence not in Primer.collection        \
             or Primer.collection[sequence]==taglength,  \
             "Primer %s must always be used with tags of the same length" % sequence
@@ -271,7 +276,7 @@ cdef tuple annotate(sequences, infos, no_tags, verbose=False):
 
     if not_aligned:
         sequences[1] = sequences[1].clone()
-        sequences[0][REVERSE_SEQUENCE_COLUMN] = sequences[1].seq             # used by alignpairedend tool
+        sequences[0][REVERSE_SEQUENCE_COLUMN] = sequences[1].seq        # used by alignpairedend tool
         sequences[0][REVERSE_QUALITY_COLUMN] = sequences[1].quality     # used by alignpairedend tool
 
     for seq in sequences:
@@ -299,7 +304,7 @@ cdef tuple annotate(sequences, infos, no_tags, verbose=False):
             directmatch.append((p, p(seq, same_sequence=not new_seq, pattern=pattern), seq, p))
             new_seq = False
             pattern+=1
-    
+        
     # Choose match closer to the start of (one of the) sequence(s)
     directmatch = sorted(directmatch, key=sortMatch)
     all_direct_matches = directmatch

python/obitools3/commands/rm.pyx

@@ -5,7 +5,9 @@ from obitools3.apps.config import logger
 from obitools3.dms import DMS
 from obitools3.apps.optiongroups import addMinimalInputOption
 from obitools3.dms.view.view cimport View
+from obitools3.utils cimport tostr
 import os
+import shutil
  
 __title__="Delete a view"
 
@@ -30,15 +32,56 @@ def run(config):
     else: 
         raise NotImplementedError()
     
+    dms = input[0]
+    
     # Get the path to the view file to remove
-    path = input[0].full_path  # dms path
-    path+=b"/VIEWS/"
-    path+=view.name
-    path+=b".obiview"
+    path = dms.full_path  # dms path
+    view_path=path+b"/VIEWS/"
+    view_path+=view.name
+    view_path+=b".obiview"
+    
+    to_remove = {}
+    # For each column:
+    for col_alias in view.keys():
+        col = view[col_alias]
+        col_name = col.original_name
+        col_version = col.version
+        col_type = col.data_type
+        col_ref = (col_name, col_version)
+        # build file name and AVL file names
+        col_file_name = f"{tostr(path)}/{tostr(col.original_name)}.obicol/{tostr(col.original_name)}@{col.version}.odc"
+        if col_type in [b'OBI_CHAR', b'OBI_QUAL', b'OBI_STR', b'OBI_SEQ']:
+            avl_file_name = f"{tostr(path)}/OBIBLOB_INDEXERS/{tostr(col.original_name)}_{col.version}_indexer"
+        else:
+            avl_file_name = None
+        to_remove[col_ref] = [col_file_name, avl_file_name]
+    
+    # For each view:
+    do_not_remove = []
+    for vn in dms:
+        v = dms[vn]
+        # ignore the one being deleted
+        if v.name != view.name:
+            # check that none of the column is referenced, if referenced, remove from list to remove
+            cols = [(v[c].original_name, v[c].version) for c in v.keys()]
+            for col_ref in to_remove:
+                if col_ref in cols:
+                    do_not_remove.append(col_ref)
+    
+    for nr in do_not_remove:
+        to_remove.pop(nr)
     
     # Close the view and the DMS
     view.close()
     input[0].close(force=True)
     
-    # Rm
-    os.remove(path)
+    #print(to_remove)
+    
+    # rm AFTER view and DMS close
+    os.remove(view_path)
+    for col in to_remove:
+        os.remove(to_remove[col][0])
+        if to_remove[col][1] is not None:
+            shutil.rmtree(to_remove[col][1])
+        
+        

python/obitools3/dms/taxo/taxo.pyx

@@ -325,8 +325,9 @@ cdef class Taxonomy(OBIWrapper) :
         cdef Taxon taxon
         try:
             taxon = self.get_taxon_by_taxid(taxid)
-        except:
-            raise StopIteration
+        except Exception as e:
+            print('\n'+e, file=sys.stderr)
+            return 
         if taxon is not None:
             while taxon.taxid != 1:
                 yield taxon
@@ -334,7 +335,7 @@ cdef class Taxonomy(OBIWrapper) :
                 taxon = taxon.parent
             yield taxon
         else:
-            raise StopIteration
+            return
 
 
     def is_ancestor(self, int ancestor_taxid, int taxid):

python/obitools3/format/tab.pyx

@@ -23,16 +23,17 @@ cdef class TabFormat:
     @cython.boundscheck(False)    
     def __call__(self, object data):
         
-        cdef set ktags
+        cdef object ktags
         cdef list tags = [key for key in data]
         
         line = []
-        
-        if self.tags is not None and self.tags:
-            ktags = self.tags
+        if self.tags != None and self.tags:
+            ktags = list(self.tags)
         else:
-            ktags = set(tags)            
-                
+            ktags = list(set(tags))   
+                     
+        ktags.sort()
+                        
         if self.header and self.first_line:
             for k in ktags:
                 if k in tags:

python/obitools3/parsers/fastq.pyx

@@ -103,7 +103,11 @@ def fastqWithQualityIterator(lineiterator,
         yield seq
 
         read+=1
-        hline = next(i)
+        try:
+            hline = next(i)
+        except StopIteration:
+            return
+
     
 
 def fastqWithoutQualityIterator(lineiterator, 
@@ -174,5 +178,7 @@ def fastqWithoutQualityIterator(lineiterator,
         yield seq
     
         read+=1
-        hline = next(i)
-        
+        try:
+            hline = next(i)
+        except StopIteration:
+            return        

python/obitools3/parsers/tab.pyx

@@ -99,7 +99,10 @@ def tabIterator(lineiterator,
         
         read+=1
         
-        line = next(iterator)
+        try:
+            line = next(iterator)
+        except StopIteration:
+            return 
     
         
         

python/obitools3/uri/decode.pyx

@@ -280,7 +280,7 @@ def open_uri(uri,
             iseq = urib
             objclass = bytes
     else:  # TODO update uopen to be able to write? 
-        if config['obi']['outputformat'] == b'metabaR':
+        if 'outputformat' in config['obi'] and config['obi']['outputformat'] == b'metabaR':
             if 'metabarprefix' not in config['obi']:
                 raise Exception("Prefix needed when exporting for metabaR (--metabaR-prefix option)")
             else:

python/obitools3/version.py

@@ -1,5 +1,5 @@
 major = 3
 minor = 0
-serial= '1b21'
+serial= '1b26'
 
 version ="%d.%d.%s" % (major,minor,serial)

src/obi_ecopcr.c

@@ -365,8 +365,6 @@ static int print_seq(Obiview_p i_view, Obiview_p o_view,
 
 	int32_t i;
 
-	// TODO add check for primer longer than MAX_PAT_LEN (32)
-
 	// Get sequence id
 	seq_id = obi_get_str_with_elt_idx_and_col_p_in_view(i_view, i_id_column, i_idx, 0);
 
@@ -751,6 +749,20 @@ int obi_ecopcr(const char* i_dms_name,
 	o1c = complementPattern(o1);
 	o2c = complementPattern(o2);
 
+	// check for primers equal or longer than MAX_PAT_LEN (32)
+	if (strlen(primer1) >= MAX_PAT_LEN)
+	{
+		obi_set_errno(OBI_ECOPCR_ERROR);
+		obidebug(1, "\nError: first primer is too long, needs to be < 32bp (%s)", primer1);
+		return -1;
+	}
+	if (strlen(primer2) >= MAX_PAT_LEN)
+	{
+		obi_set_errno(OBI_ECOPCR_ERROR);
+		obidebug(1, "\nError: second primer is too long, needs to be < 32bp (%s)", primer2);
+		return -1;
+	}
+
 	// Open input DMS
 	i_dms = obi_open_dms(i_dms_name, false);
 	if (i_dms == NULL)