问大型文件的第一行上的多个替换

EN

仅在文件的第一行中将s[1-4]替换为L[1-4]，将s[5-8]替换为W[1-4]：

sed -Ee '1s/s([1-4])/L\1/g' -e '1s/s([5-8])/W\1/g' -e '1y/5678/1234/' -e '1q' file

演示：

$ cat文件 启动端链ref_context repeat_masked s1_smpl_context s1_c_count s1_ct_count s1_non_ct_count s1_m% s1_score s1_snp s1_indels s2_smpl_context s2_c_count s2_ct_count s2_non_ct_count s2_m% s2_non_ct_count s2_m% s2_score s2_snp s2_m%s2_m%s2_snp s2_m%s2_snp s2_m%s2_m%s2_snp s2_snp end 20 en22 en23 en25s4_c_count s4_ct_count s4_non_ct_count s4_m% s4_score s4_snp s4_indels s5_smpl_context s5_c_count s5_ct_count s5_non_ct_count s5_m% s5_score s5_snp s5_indels s6_smpl_context s5_indels s6_c_count s5_indels s6_smpl_context s5_indels s6_c_count s5_indels s5_indels s6_c_count s6_c_count s5_indels s6_c_count_count s7_m% s7_score s7_snp s7_indels s8_smpl_context s8_c_count s8_ct_count s8_non_ct_count s8_m% s8_score s8_snp s8_indels s1_line_2 s3_line_3 s8_line_4 $ sed -Ee‘1s/s(1-4)/L/g’-e‘1s/s(5-8)/W1/g’-e '1y/5678/1234/‘-e '1q’文件 启动端链ref_context repeat_masked L1_smpl_context L1_c_count L1_ct_count L1_non_ct_count L1_m% L1_score L1_snp L1_indels L2_smpl_context L2_c_count L2_ct_count L2_non_ct_count L2_m% L2_non_ct_count L2_m% L2_score L2_snp L2_m%L2_m%L2_snp L2_m%L2_snp L2_m%L2_m%L2_snp L2_snp end 20 en22 en23 en25L4_c_count L4_ct_count L4_non_ct_count L4_m% L4_score L4_snp L4_indels W1_smpl_context W1_c_count W1_ct_count W1_non_ct_count W1_m% W1_score W1_snp W1_indels W2_smpl_context W1_indels W2_c_count W1_indels W2_smpl_context W1_indels W2_c_count W1_indels W1_indels W2_c_count W2_c_count W1_indels W2_c_count_count W3_m% W3_score W3_snp W3_indels W4_smpl_context W4_c_count W4_ct_count W4_non_ct_count W4_m% W4_score W4_snp W4_indels

由于您的替换没有改变第一行的长度，您还可以选择直接修改原始文件。我不认为您可以使用任何常见的shell命令来完成这个任务，但是您可以用Python编写一个程序来完成这个任务。

然而，我只会考虑这个选项，如果文件是如此巨大，以至于您无法临时复制它。

#!/usr/bin/env python

import os

# On windows, you need to use os.O_RDWR | os.O_BINARY
fd = os.open('modex', os.O_RDWR)
f = os.fdopen(fd)
f.seek(0)
line = f.readline()
replacements = [("s%s" % x, "L%s" % x) for x in range(1,5)] \
        + [("s%s" % (x+4), "W%s" % x) for x in range(1,5)]
for (s,r) in replacements:
    line = line.replace(s, r)
# We cannot use python file objects here, because f.write() _always_ appends,
# regardless of the seek position. So we use the raw object here.
# Mixing raw IO and python IO should be done with care, however we should be
# ok here, as we did not write anything yet.
os.lseek(fd, 0, os.SEEK_SET)
os.write(fd, line)
f.close()