Commit 847c9c81 authored by MercierC's avatar MercierC

import: fixed count estimation for tabular files with header

parent 6026129c
......@@ -389,10 +389,7 @@ def open_uri(uri,
sep = tobytes(qualifiers[b"sep"][0][0])
else:
try:
sep = config["obi"]["sep"]
if sep == '\\t': # dirty workaround for flake8(?) issue that reads '\t' as '\'+'t' when parsing the option value
sep = '\t'
sep = tobytes(sep)
sep = tobytes(config["obi"]["sep"])
except KeyError:
sep=None
......@@ -568,6 +565,6 @@ def open_uri(uri,
entry_count = -1
if input:
entry_count = count_entries(file, format)
entry_count = count_entries(file, format, header)
return (file, iseq, objclass, urib, entry_count)
......@@ -3,7 +3,7 @@
from obitools3.dms.capi.obitypes cimport obitype_t, index_t
cpdef bytes format_uniq_pattern(bytes format)
cpdef int count_entries(file, bytes format)
cpdef int count_entries(file, bytes format, bint header)
cdef obi_errno_to_exception(index_t line_nb=*, object elt_id=*, str error_message=*)
......
......@@ -40,7 +40,7 @@ cpdef bytes format_uniq_pattern(bytes format):
return None
cpdef int count_entries(file, bytes format):
cpdef int count_entries(file, bytes format, bint header):
try:
sep = format_uniq_pattern(format)
......@@ -75,6 +75,8 @@ cpdef int count_entries(file, bytes format):
total_count += len(re.findall(sep, mmapped_file))
if format != b"ngsfilter" and format != b"tabular" and format != b"embl" and format != b"genbank" and format != b"fastq":
total_count += 1 # adding +1 for 1st entry because separators include \n (ngsfilter and tabular already count one more because of last \n)
if format == b"tabular" and header: # not counting header as an entry
total_count -= 1
except:
if len(files) > 1:
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment