zzh
/
gatk-3.8
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add ability for flat file table parsing module to skip ahead to first occurence of a regular expression (use case: consistently parsing DepthOfCoverage output for histogram section of file across file format changes) 

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@2377 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
andrewk 2009-12-16 20:38:50 +00:00
parent b626fc0684
commit f5e547ed6e
1 changed files with 20 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
python/FlatFileTable.py
View File

@ -2,15 +2,31 @@
import sys, itertools import sys, itertools
def record_generator(filename, sep="\t", skip_n_lines=0): def record_generator(filename, sep="\t", skip_n_lines=0, skip_until_regex_line=""):
"""Given a file with field headers on the first line and records on subsequent lines, """Given a file with field headers on the first line and records on subsequent lines,
generates a dictionary for each line keyed by the header fields""" generates a dictionary for each line keyed by the header fields"""
fin = open(filename) fin = open(filename)
for i in range(skip_n_lines): # Skip a number of lines if skip_n_lines > 0:
fin.readline() for i in range(skip_n_lines): # Skip a number of lines
fin.readline()
header = fin.readline().rstrip().split(sep) # Pull off header found_regex = False
if skip_until_regex_line != "":
import re
regex_line = re.compile(skip_until_regex_line)
for line in fin:
match = regex_line.search(line)
if match:
found_regex = line
break
if not found_regex:
print "Warning: Regex "+skip_until_regex_line+" not found in FlatFileTable:record_generator"
if found_regex:
header = found_regex.rstrip().split(sep) # Parse header
else:
header = fin.readline().rstrip().split(sep) # Pull off header
for line in fin: # for line in fin: #
fields = line.rstrip().split(sep) fields = line.rstrip().split(sep)