obitools/obitools3
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 66 Wiki Activity

import: fixed count estimation for tabular files with header

Browse Source
This commit is contained in:
MercierC
2021-03-30 09:07:14 +13:00
parent 6026129ca8
commit 847c9c816d
3 changed files with 6 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
python/obitools3/uri/decode.pyx
View File

@ -389,10 +389,7 @@ def open_uri(uri,
sep = tobytes(qualifiers[b"sep"][0][0]) sep = tobytes(qualifiers[b"sep"][0][0])
else: else:
try: try:
sep = config["obi"]["sep"] sep = tobytes(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)
except KeyError: except KeyError:
sep=None sep=None
@ -568,6 +565,6 @@ def open_uri(uri,
entry_count = -1 entry_count = -1
if input: if input:
entry_count = count_entries(file, format) entry_count = count_entries(file, format, header)
return (file, iseq, objclass, urib, entry_count) return (file, iseq, objclass, urib, entry_count)

2
python/obitools3/utils.pxd
View File

@ -3,7 +3,7 @@
from obitools3.dms.capi.obitypes cimport obitype_t, index_t from obitools3.dms.capi.obitypes cimport obitype_t, index_t
cpdef bytes format_uniq_pattern(bytes format) 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=*) cdef obi_errno_to_exception(index_t line_nb=*, object elt_id=*, str error_message=*)

4
python/obitools3/utils.pyx
View File

@ -40,7 +40,7 @@ cpdef bytes format_uniq_pattern(bytes format):
return None return None
cpdef int count_entries(file, bytes format): cpdef int count_entries(file, bytes format, bint header):
try: try:
sep = format_uniq_pattern(format) sep = format_uniq_pattern(format)
@ -75,6 +75,8 @@ cpdef int count_entries(file, bytes format):
total_count += len(re.findall(sep, mmapped_file)) 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": 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) 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: except:
if len(files) > 1: if len(files) > 1: