hyung-hwan/qse
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

added the 'k' option to the 's' command in sed

Browse Source
This commit is contained in:
hyung-hwan 2014-02-19 04:09:46 +00:00
parent 9006c44b9a
commit b5de91921c
3 changed files with 46 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
qse/doc/page/sed-cmd.md
View File

@ -187,6 +187,8 @@ with *repl*. An ampersand(&) in *repl* refers to the matching substring.
- *p* prints pattern space if a successful replacement was made
- *w* file writes pattern space to *file* if a successful replacement
was made. It, if specified, should be the last option.
- *k* removes(kills) unmached portions from the pattern space. It is
useful for partial extraction.
### y/src/dst/ ###
Replaces all occurrences of characters in *src* with characters in *dst*.
@ -236,6 +238,18 @@ first and the first line last.
### s/[[:space:]]{2,}/ /g ###
Compacts whitespaces if #QSE_SED_EXTENDEDREX is on.
### s/[0-9]/&/gk ###
Extract all digits.
$ echo "Q123Q456" | qsesed -r 's/[0-9]+/&/gk'
123456
### s/[0-9]+/&/2k ###
Extract the second number.
$ echo "Q123Q456" | qsesed -r 's/[0-9]+/&/2k'
456
### C/d:,f3,1/ ###
Prints the third field and the first field from a colon separated text.

1
qse/include/qse/sed/sed.h
View File

@ -171,6 +171,7 @@ struct qse_sed_cmd_t
unsigned short g: 1; /* global */
unsigned short p: 1; /* print */
unsigned short i: 1; /* case insensitive */
unsigned short k: 1; /* kill unmatched portion */
} subst;
/* translation set for the y command */

38
qse/lib/sed/sed.c
View File

@ -1383,6 +1383,11 @@ static int get_subst (qse_sed_t* sed, qse_sed_cmd_t* cmd)
cmd->u.subst.g = 1;
NXTSC_GOTO (sed, c, oops);
}
else if (c == QSE_T('k'))
{
cmd->u.subst.k = 1;
NXTSC_GOTO (sed, c, oops);
}
else if (c >= QSE_T('0') && c <= QSE_T('9'))
{
unsigned long occ;
@ -2833,14 +2838,18 @@ static int do_subst (qse_sed_t* sed, qse_sed_cmd_t* cmd)
if (n == 0)
{
/* no more match found */
if (qse_str_ncat (
&sed->e.txt.scratch,
cur.ptr, cur.len) == (qse_size_t)-1)
/* no more match found or substitution occurrence matched.
* copy the remaining portion and finish */
if (!cmd->u.subst.k)
{
/* copy the remaining portion */
m = qse_str_ncat (&sed->e.txt.scratch, cur.ptr, cur.len);
if (m == (qse_size_t)-1)
{
SETERR0 (sed, QSE_SED_ENOMEM, QSE_NULL);
return -1;
}
}
break;
}
@ -2854,11 +2863,16 @@ static int do_subst (qse_sed_t* sed, qse_sed_cmd_t* cmd)
if (max_count > 0 && sub_count + 1 != max_count)
{
if (cur.ptr < str_end)
/* substition occurrence specified.
* but this is not the occurrence yet */
if (!cmd->u.subst.k && cur.ptr < str_end)
{
/* copy the unmatched portion and the matched portion
* together as if the matched portion was not matched */
m = qse_str_ncat (
&sed->e.txt.scratch,
cur.ptr, mat.ptr-cur.ptr+mat.len
cur.ptr, mat.ptr - cur.ptr + mat.len
);
if (m == (qse_size_t)-1)
{
@ -2869,12 +2883,14 @@ static int do_subst (qse_sed_t* sed, qse_sed_cmd_t* cmd)
}
else
{
/* perform actual substitution */
repl = 1;
if (cur.ptr < str_end)
if (!cmd->u.subst.k && cur.ptr < str_end)
{
m = qse_str_ncat (
&sed->e.txt.scratch, cur.ptr, mat.ptr-cur.ptr
&sed->e.txt.scratch, cur.ptr, mat.ptr - cur.ptr
);
if (m == (qse_size_t)-1)
{
@ -2902,8 +2918,10 @@ static int do_subst (qse_sed_t* sed, qse_sed_cmd_t* cmd)
else
{
#endif
/* the know speical characters have been escaped
* in get_subst(). so i don't call trans_escaped() here */
/* Known speical characters have been escaped
* in get_subst(). so i don't call trans_escaped() here.
* It's a normal character that's escaped.
* For example, \1 is just 1. and \M is just M. */
m = qse_str_ccat (&sed->e.txt.scratch, nc);
#ifndef USE_REX
}