mirrors/wordsplit
1
0
Fork 0
mirror of git://git.gnu.org.ua/wordsplit.git synced 2025-04-26 00:29:54 +03:00
Code Issues Projects Releases Packages Wiki Activity Actions

Implement default assignments, etc.

Browse source 
* src/wordsplit.c: Implement default assignment, word
expansion in variable defaults, distinction between
${variable:-word} and ${variable-word}.
* doc/wordsplit.3: New file.
* src/wordsplit.h (wordsplit)<ws_envbuf,ws_envidx>
<ws_envsiz>: New members.
(WRDSF_ARGV): Remove.
(WRDSF_OPTIONS): New flag.
(WRDSO_ARGV): New option bit.
* tests/wordsplit.at: Add new tests.
* tests/wsp.c: Set WRDSF_OPTIONS flag if one of the options is requested.
This commit is contained in:
Sergey Poznyakoff 2014-10-28 15:40:20 +02:00
parent 73180a045d
commit 9bebcfbc1c
5 changed files with 1007 additions and 109 deletions
Download patch file Download diff file Expand all files Collapse all files

585
doc/wordsplit.3 Normal file
View file

@ -0,0 +1,585 @@
.\" This file is part of grecs -*- nroff -*-
.\" Copyright (C) 2007, 2009-2014 Sergey Poznyakoff
.\"
.\" Grecs is free software; you can redistribute it and/or modify
.\" it under the terms of the GNU General Public License as published by
.\" the Free Software Foundation; either version 3, or (at your option)
.\" any later version.
.\"
.\" Grecs is distributed in the hope that it will be useful,
.\" but WITHOUT ANY WARRANTY; without even the implied warranty of
.\" MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
.\" GNU General Public License for more details.
.\"
.\" You should have received a copy of the GNU General Public License
.\" along with Grecs. If not, see <http://www.gnu.org/licenses/>.
.\"
.TH WORDSPLIT 3 "October 28, 2014" "GRECS" "Grecs User Reference"
.SH NAME
wordsplit \- split string into words
.SH SYNOPSIS
.B #include <wordsplit.h>
.sp
\fBint wordsplit (const char *\fIs\fB,\
wordsplit_t *\fIws\fB, int \fIflags\fB);\fR
.sp
\fBint wordsplit_len (const char *\fIs\fB,\
\fBsize_t \fIlen\fR,\
\fBwordsplit_t *\fIp\fB,\
int \fIflags\fB);
.sp
\fBvoid wordsplit_free (wordsplit_t *\fIp\fB);\fR
.sp
\fBvoid wordsplit_free_words (wordsplit_t *\fIws\fB);\fR
.sp
\fBvoid wordsplit_perror (wordsplit_t *\fIws\fB);\fR
.sp
\fBconst char *wordsplit_strerror (wordsplit_t *\fIws\fB);\fR
.sp
\fBvoid wordsplit_clearerr (wordsplit_t *\fIws\fB);\fR
.SH DESCRIPTION
The function \fBwordsplit\fR splits the string \fIs\fR into words
using a set of rules governed by \fIflags\fR and stores the result
in the memory location pointed to by \fIws\fR. Depending on
\fIflags\fR, the function performs the following: whitespace trimming,
tilde expansion, variable expansion, quote removal, command
substitution, and path expansion. On success, the function returns 0
and stores the words found in the member \fBws_wordv\fR and the number
of words in the member \fBws_wordc\fR. On error, -1 is returned and
error code is stored in \fBws_errno\fR.
.PP
The function \fBwordsplit_len\fR acts similarly, except that it
accesses only first \fBlen\fR bytes of the string \fIs\fR, which is
not required to be null-terminated.
.PP
When no longer needed, the resources allocated by a call to one of
these functions must be freed using
.BR wordsplit_free .
.PP
The function
.B wordsplit_free_words
frees only the memory allocated for elements of
.I ws_wordv
and initializes
.I ws_wordc
to zero.
.PP
The usual calling sequence is:
.PP
.EX
wordsplit_t ws;
int rc;
if (wordsplit(s, &ws, WRDSF_DEFFLAGS)) {
wordsplit_perror(&ws);
return;
}
for (i = 0; i < ws.ws_wordc; i++) {
/* do something with ws.ws_wordv[i] */
}
wordsplit_free(&ws);
.EE
.PP
The function
.B wordsplit_perror
prints error message from the last invocation of \fBwordsplit\fR. It
uses the function pointed to by the
.I ws_error
member. By default, it outputs the message on the standard error.
.PP
For more sophisticated error reporting, the function
.B wordsplit_strerror
can be used. It returns a pointer to the string describing the error.
The caller should treat this pointer as a constant string. It should
not try to alter or deallocate it.
.PP
The function
.B wordsplit_clearerr
clears the error condition associated with \fIws\fR.
.SH EXPANSION
The number of expansions performed on the input is controlled by
appropriate bits set in the \fIflags\fR argument. Whatever expansions
are enabled, they are always run in the same order as described in this
section.
.SS Whitespace trimming
Whitespace trimming removes any leading and trailing whitespace from
the initial word array. It is enabled by the
.B WRDSF_WS
flag. Whitespace trimming is needed only if you redefine
word delimiters (\fIws_delim\fR member) so that they don't contain
whitespace characters (\fB\(dq \\t\\n\(dq\fR).
.SS Tilde expansion
Tilde expansion is enabled if the
.B WRDSF_PATHEXPAND
bit is set. It expands all words that begin with an unquoted tilde
character (`\fB~\fR'). If tilde is followed immediately by a slash,
it is replaced with the home directory of the current user (as
determined by his \fBpasswd\fR entry). A tilde alone is handled the
same way. Otherwise, the characters between the tilde and first slash
character (or end of string, if it doesn't contain any) are treated as
a login name. and are replaced (along with the tilde itself) with the
home directory of that user. If there is no user with such login
name, the word is left unchanged.
.SS Variable expansion
Variable expansion replaces each occurrence of
.BI $ NAME
or
.BI ${ NAME }
with the value of the variable \fINAME\fR. It is enabled if the
flag \fBWRDSF_NOVAR\fR is not set. The caller is responsible for
supplying the table of available variables. Two mechanisms are
provided: environment array and a callback function.
.PP
Environment array is a \fBNULL\fR-terminated array of variables,
stored in the \fIws_env\fR member. The \fBWRDSF_ENV\fR flag must be
set in order to instruct \fBwordsplit\fR to use this array.
.PP
By default, elements of the \fIws_env\fR array have the form
.IR NAME = VALUE .
An alternative format is enabled by the
.B WRDSF_ENV_KV
flag. When it is set, each variable is described by two consecutive
elements in the array:
.IR ws_env [ n ]
contains variable name, and
.IR ws_env [ "n+1" ]
contains its value.
.PP
More sophisticated variable tables can be implemented using
callback function. The \fIws_getvar\fR member should be set to point
to that function and \fBWRDSF_GETVAR\fR flag must be set. The
function itself should be defined as
.EX
int getvar (char **ret, const char *var, size_t len, void *clos);
.EE
.PP
The function should look up for the variable identified by the first
\fIlen\fR bytes of the string \fIvar\fR. If such variable is found,
th function stores a copy of its value (allocated using
\fBmalloc\fR(3)) in the memory location pointed to by \fBret\fR, and
returns \fBWRDSE_OK\fR. If the variable is not found, the function
returns \fBWRDSE_UNDEF\fR. Otherwise, a non NULL error code is
returned.
.PP
If \fIws_getvar\fR returns
.BR WRDSE_USERERR ,
it must store the pointer to the error description string in
.BR *ret .
In any case (whether returning \fB0\fR or \fBWRDSE_USERERR\fR) , the
data returned in \fBret\fR must be allocated using
.BR malloc (3).
.PP
If both
.I ws_env
and
.I ws_getvar
are used, the variable is first looked up in
.IR ws_env ,
and if not found there, the
.I ws_getvar
function is called.
.PP
During variable expansion, the forms below cause
.B wordsplit
to test for a variable that is unset or null. Omitting the
colon results in a test only for a variable that is unset.
.TP
.BI ${ variable :- word }
.BR "Use Default Values" .
If \fIvariable\fR is unset or null, the expansion of \fIword\fR is substituted.
Otherwise, the value of \fIvariable\fR is substituted.
.TP
.BI ${ variable := word }
.BR "Assign Default Values" .
If \fIvariable\fR is unset or null, the expansion of \fIword\fR is
assigned to \fIvariable\fR. The value of \fIvariable\fR is then substituted.
.TP
.BI ${ variable :? word }
.BR "Display Error if Null or Unset" .
If \fIvariable\fR is null or unset, the expansion of \fIword\fR (or a
message to that effect if word is not present) is output using
.IR ws_error .
Otherwise, the value of \fIvariable\fR is substituted.
.TP
.BI ${ variable :+ word }
.BR "Use Alternate Value" .
If \fIvariable\fR is null or unset, nothing is substituted, otherwise the
expansion of \fIword\fR is substituted.
.SS Quote removal
.SS Command substitution
.SS Path expansion
.SH WORDSPLIT_T STRUCTURE
The data type \fBwordsplit_t\fR has three members that contain
output data upon return from \fBwordsplit\fR or \fBwordsplit_len\fR,
and a number of members that the caller can initialize on input in
order to customize the function behavior. Each its member has a
corresponding flag bit, which must be set in the \fIflags\fR argument
in order to instruct the \fBwordsplit\fR function to use it.
.SS OUTPUT
.TP
.BI size_t " ws_wordc"
Number of words in \fIws_wordv\fR. Accessible upon successful return
from \fBwordsplit\fR.
.TP
.BI "char ** " ws_wordv
Array of resulting words. Accessible upon successful return
from \fBwordsplit\fR.
.TP
.BI "int " ws_errno
Error code, if the invocation of \fBwordsplit\fR or
\fBwordsplit_len\fR failed. This is the same value as returned from
the function in that case.
.SS INPUT
.TP
.BI "size_t " ws_offs
If the
.B WRDSF_DOOFFS
flag is set, this member specifies the number of initial elements in
.I ws_wordv
to fill with NULLs. These elements are not counted in the returned
.IR ws_wordc .
.TP
.BI "int " ws_flags
Contains flags passed to wordsplit on entry. Can be used as a
read-only member when using \fBwordsplit\fR in incremental mode or
in a loop with
.B WRDSF_REUSE
flag set.
.TP
.BI "int " ws_options
Additional options used when
.B WRDSF_OPTIONS
is set.
.TP
.BI "const char *" ws_delim
Word delimiters. If initialized on input, the
.B WRDSF_DELIM
flag must be set. Otherwise, it is initialized on entry to
.B wordsplit
with the string \fB\(dq \\t\\n\(dq\fR.
.TP
.BI "const char *" ws_comment
A zero-terminated string of characters that begin an inline comment.
If initialized on input, the
.B WRDSF_COMMENT
flag must be set. By default, it's value is \fB\(dq#\(dq\fR.
.TP
.BI "const char *" ws_escape
Characters to be escaped with backslash. The
.B WRDSF_ESCAPE
flag must be set if this member is initialized.
.TP
.BI "void (*" ws_alloc_die ") (wordsplit_t *)"
This function is called when
.B wordsplit
is unable to allocate memory and the
.B WRDSF_ENOMEMABRT
flag was set. The default function prints a
message on standard error and aborts. This member can be used
to customize error handling. If initialized, the
.B WRDSF_ALLOC_DIE
flag must be set.
.TP
.BI "void (*" ws_error ") (const char *, ...)"
Pointer to function used for error reporting. The invocation
convention is the same as for
.BR printf (3).
The default function formats and prints the message on the standard
error.
If this member is initialized, the
.B WRDSF_ERROR
flag must be set.
.TP
.BI "void (*" ws_debug ") (const char *, ...)"
Pointer to function used for debugging output. By default it points
to the same function as
.BR ws_error .
If initialized, the
.B WRDSF_DEBUG
flag must be set.
.TP
.BR "const char **" ws_env
A \fBNULL\fR-terminated array of environment variables. It is used
during variable expansion. If set, the
.B WRDSF_ENV
flag must be set. Variable expansion is enabled only if either
.B WRDSF_ENV
or
.B WRDSF_GETVAR
(see below) is set, and
.B WRDSF_NOVAR
flag is not set.
Each element of
.I ws_env
must have the form \fB\(dq\fINAME\fB=\fIVALUE\fR, where \fINAME\fR is
the name of the variable, and \fIVALUE\fR is its value.
Alternatively, if the \fBWRDSF_ENV_KV\fR flag is set, each variable is
described by two elements of
.IR ws_env : one containing variable name, and the next one with its
value.
.TP
.BI "int (*" ws_getvar ") (char **ret, const char *var, size_t len, void *clos)"
Points to the function that will be used during variable expansion to
look up for the value of the environment variable named \fBvar\fR.
This function is used if the variable expansion is enabled (i.e. the
.B WRDSF_NOVAR
flag is not set), and the \fBWRDSF_GETVAR\fR flag is set.
If both
.B WRDSF_ENV
and
.B WRDSF_GETVAR
are set, the variable is first looked up in the
.I ws_env
array and, if not found there,
.I ws_getvar
is called.
The name of the variable is specified by the first \fIlen\fR bytes of
the string \fIvar\fR. The \fIclos\fR parameter supplies the
user-specific data (see below the description of \fIws_closure\fR
member) and the \fBret\fR parameter points to the memory location used
for output data. On success, the function must store ther a pointer
to the string with the value of the variable and return 0. On error,
it must return one of the error codes described in the section
.BR "ERROR CODES" .
If \fIws_getvar\fR returns
.BR WRDSE_USERERR ,
it must store the pointer to the error description string in
.BR *ret .
In any case (whether returning \fB0\fR or \fBWRDSE_USERERR\fR) , the
data returned in \fBret\fR must be allocated using
.BR malloc (3).
.TP
.BI "void *" ws_closure
Additional user-specific data passed as the last argument to
.I ws_getvar
or
.I ws_command
(see below). If defined, the
.B WRDSF_CLOSURE
flag must be set.
.TP
\fBint (*\fIws_command\fB)\
(char **ret,\
const char *cmd,\
size_t len,\
char **argv,\
void *clos)
Pointer to the function that performs command substitution. It treats
the first \fIlen\fR bytes of the string \fIcmd\fR as a command
(whatever it means for the caller) and attempts to execute it. On
success, a pointer to the string with the command output is stored
in the memory location pointed to by \fBret\fR and \fB0\fR is
returned. On error,
the function must return one of the error codes described in the section
.BR "ERROR CODES" .
If \fIws_getvar\fR returns
.BR WRDSE_USERERR ,
it must store the pointer to the error description string in
.BR *ret .
In any case (whether returning \fB0\fR or \fBWRDSE_USERERR\fR) , the
data returned in \fBret\fR must be allocated using
.BR malloc (3).
If the
.I WRDSO_ARGV
option is set, the parameter \fBargv\fR contains the command split into
words using the same settings as the input \fIws\fR structure, with
command substitution disabled.
The \fIclos\fR parameter supplies user-specific data (see the
description of \fIws_closure\fR member).
.SH FLAGS
The following macros are defined for use in the \fBflags\fR argument.
.TP
.B WRDSF_DEFFLAGS
Default flags. This is a shortcut for:
\fB(WRDSF_NOVAR |\
WRDSF_NOCMD |\
WRDSF_QUOTE |\
WRDSF_SQUEEZE_DELIMS |\
WRDSF_CESCAPES)\fR,
i.e.: disable variable expansion and quote substituton, perform quote
removal, treat any number of consequtive delimiters as a single
delimiter, replace \fBC\fR escapes appearing in the input string with
the corresponding characters.
.TP
.B WRDSF_APPEND
Append the words found to the array resulting from a previous call to
\fBwordsplit\fR.
.TP
.B WRDSF_DOOFFS
Insert
.I ws_offs
initial
.BR NULL s
in the array
.IR ws_wordv .
These are not counted in the returned
.IR ws_wordc .
.TP
.B WRDSF_NOCMD
Don't do command substitution.
.TP
.B WRDSF_REUSE
The parameter \fIws\fR resulted from a previous call to
\fBwordsplit\fR, and \fBwordsplit_free\fR was not called. Reuse the
allocated storage.
.TP
.B WRDSF_SHOWERR
Print errors using
.BR ws_error .
.TP
.B WRDSF_UNDEF
Consider it an error if an undefined variable is expanded.
.TP
.B WRDSF_NOVAR
Don't do variable expansion.
.TP
.B WRDSF_ENOMEMABRT
Abort on
.B ENOMEM
error. By default, out of memory errors are treated as any other
errors: the error is reported using \fIws_error\fR if the
.B WRDSF_SHOWERR
flag is set, and error code is returned. If this flag is set, the
.B ws_alloc_die
function is called instead. This function is not supposed to return.
.TP
.B WRDSF_WS
Trim off any leading and trailind whitespace from the returned
words. This flag is useful if the \fIws_delim\fR member does not
contain whitespace characters.
.TP
.B WRDSF_SQUOTE
Handle single quotes.
.TP
.B WRDSF_DQUOTE
Handle double quotes.
.TP
.B WRDSF_QUOTE
A shortcut for \fB(WRDSF_SQUOTE|WRDSF_DQUOTE)\fR.
.TP
.B WRDSF_SQUEEZE_DELIMS
Replace each input sequence of repeated delimiters with a single
delimiter.
.TP
.B WRDSF_RETURN_DELIMS
Return delimiters.
.TP
.B WRDSF_SED_EXPR
Treat
.BR sed (1) expressions as words.
.TP
.B WRDSF_DELIM
.I ws_delim
member is initialized.
.TP
.B WRDSF_COMMENT
.I ws_comment
member is initialized.
.TP
.B WRDSF_ALLOC_DIE
.I ws_alloc_die
member is initialized.
.TP
.B WRDSF_ERROR
.I ws_error
member is initialized.
.TP
.B WRDSF_DEBUG
.I ws_debug
member is initialized.
.TP
.B WRDSF_ENV
.I ws_env
member is initialized.
.TP
.B WRDSF_GETVAR
.I ws_getvar member is initialized.
.TP
.B WRDSF_SHOWDBG
Enable debugging.
.TP
.B WRDSF_NOSPLIT
Don't split input into words. This flag is is useful for side
effects, e.g. to perform variable expansion within a string.
.TP
.B WRDSF_KEEPUNDEF
Keep undefined variables in place, instead of expanding them to
empty strings.
.TP
.B WRDSF_WARNUNDEF
Warn about undefined variables.
.TP
.B WRDSF_CESCAPES
Handle \fBC\fR-style escapes in the input string.
.TP
.B WRDSF_CLOSURE
.I ws_closure
is set.
.TP
.B WRDSF_ENV_KV
Each two consecutive elements in the
.I ws_env
array describe a single variable:
.IR ws_env [ n ]
contains variable name, and
.IR ws_env [ "n+1" ]
contains its value.
.TP
.B WRDSF_ESCAPE 0x10000000
.I ws_escape
is set.
.TP
.B WRDSF_INCREMENTAL
Incremental mode. Each subsequent call to \fBwordsplit\fR with
\fBNULL\fR as its first argument parses the next word from the input.
See the section
.B INCREMENTAL MODE
for a detailed discussion.
.TP
.B WRDSF_PATHEXPAND
Perform pathname and tilde expansion. If this flag is set, the
\fIws_options\fR member must also be initialized. See the
subsection
.B "Pathname expansion"
for details.
.TP
.B WRDSF_OPTIONS
The
.I ws_options
member is initialized.
.SH "RETURN VALUE"
.SH EXAMPLE
.SH "SEE ALSO"
.SH AUTHORS
Sergey Poznyakoff
.SH "BUG REPORTS"
Report bugs to <gray+grecs@gnu.org.ua>.
.SH COLOPHON
The \fBGrecs\fR library is constantly changing, so this manual page
may be incorrect or out-of-date. For the latest copy of \fBGrecs\fR
documentation, visit <http://www.gnu.org.ua/software/grecs>.
.SH COPYRIGHT
Copyright \(co 2011 Sergey Poznyakoff
.br
.na
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
.br
.ad
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.
.\" Local variables:
.\" eval: (add-hook 'write-file-hooks 'time-stamp)
.\" time-stamp-start: ".TH [A-Z_][A-Z0-9_]* [0-9] \""
.\" time-stamp-format: "%:B %:d, %:y"
.\" time-stamp-end: "\""
.\" time-stamp-line-limit: 20
.\" end:

377
src/wordsplit.c
View file

@ -114,11 +114,30 @@ _wsplt_subsplit (struct wordsplit *wsp, struct wordsplit *wss,
wss->ws_error = wsp->ws_error;
wss->ws_alloc_die = wsp->ws_alloc_die;
if (!(flags & WRDSF_NOVAR))
{
wss->ws_env = wsp->ws_env;
wss->ws_getvar = wsp->ws_getvar;
flags |= wsp->ws_flags & (WRDSF_ENV | WRDSF_ENV_KV | WRDSF_GETVAR);
}
if (!(flags & WRDSF_NOCMD))
{
wss->ws_command = wsp->ws_command;
}
if ((flags & (WRDSF_NOVAR|WRDSF_NOCMD)) != (WRDSF_NOVAR|WRDSF_NOCMD))
{
wss->ws_closure = wsp->ws_closure;
flags |= wsp->ws_flags & WRDSF_CLOSURE;
}
wss->ws_options = wsp->ws_options;
flags |= WRDSF_DELIM
| WRDSF_ALLOC_DIE
| WRDSF_ERROR
| WRDSF_DEBUG
| (wsp->ws_flags & (WRDSF_SHOWDBG | WRDSF_SHOWERR));
| (wsp->ws_flags & (WRDSF_SHOWDBG | WRDSF_SHOWERR | WRDSF_OPTIONS));
return wordsplit_run (str, len, wss, flags, wsp->ws_lvl + 1);
}
@ -168,12 +187,11 @@ wordsplit_init (struct wordsplit *wsp, const char *input, size_t len,
if (!(wsp->ws_flags & WRDSF_ERROR))
wsp->ws_error = _wsplt_error;
if (!(wsp->ws_flags & WRDSF_NOVAR)
&& !(wsp->ws_flags & (WRDSF_ENV | WRDSF_GETVAR)))
if (!(wsp->ws_flags & WRDSF_NOVAR))
{
_wsplt_seterr (wsp, WRDSE_USAGE);
errno = EINVAL;
return wsp->ws_errno;
/* These will be initialized on first variable assignment */
wsp->ws_envidx = wsp->ws_envsiz = 0;
wsp->ws_envbuf = NULL;
}
if (!(wsp->ws_flags & WRDSF_NOCMD))
@ -214,6 +232,9 @@ wordsplit_init (struct wordsplit *wsp, const char *input, size_t len,
if (!(wsp->ws_flags & WRDSF_CLOSURE))
wsp->ws_closure = NULL;
if (!(wsp->ws_flags & WRDSF_OPTIONS))
wsp->ws_options = 0;
wsp->ws_endp = 0;
wordsplit_init0 (wsp);
@ -717,13 +738,14 @@ find_closing_paren (const char *str, size_t i, size_t len, size_t *poff,
return 1;
}
static const char *
wordsplit_find_env (struct wordsplit *wsp, const char *name, size_t len)
static int
wordsplit_find_env (struct wordsplit *wsp, const char *name, size_t len,
char const **ret)
{
size_t i;
if (!(wsp->ws_flags & WRDSF_ENV))
return NULL;
return WRDSE_UNDEF;
if (wsp->ws_flags & WRDSF_ENV_KV)
{
@ -732,14 +754,17 @@ wordsplit_find_env (struct wordsplit *wsp, const char *name, size_t len)
{
size_t elen = strlen (wsp->ws_env[i]);
if (elen == len && memcmp (wsp->ws_env[i], name, elen) == 0)
return wsp->ws_env[i + 1];
{
*ret = wsp->ws_env[i + 1];
return WRDSE_OK;
}
/* Skip the value. Break the loop if it is NULL. */
i++;
if (wsp->ws_env[i] == NULL)
break;
}
}
else
else if (wsp->ws_env)
{
/* Usual (A=B) environment. */
for (i = 0; wsp->ws_env[i]; i++)
@ -751,10 +776,117 @@ wordsplit_find_env (struct wordsplit *wsp, const char *name, size_t len)
if (name[j] != var[j])
break;
if (j == len && var[j] == '=')
return var + j + 1;
{
*ret = var + j + 1;
return WRDSE_OK;
}
}
}
return NULL;
return WRDSE_UNDEF;
}
static int
wsplt_assign_var (struct wordsplit *wsp, const char *name, size_t namelen,
char *value)
{
int n = (wsp->ws_flags & WRDSF_ENV_KV) ? 2 : 1;
char *v;
if (wsp->ws_envidx + n >= wsp->ws_envsiz)
{
size_t sz;
char **newenv;
if (!wsp->ws_envbuf)
{
if (wsp->ws_flags & WRDSF_ENV)
{
size_t i = 0, j;
if (wsp->ws_env)
{
for (; wsp->ws_env[i]; i++)
;
}
sz = i + n + 1;
newenv = calloc (sz, sizeof(newenv[0]));
if (!newenv)
return _wsplt_nomem (wsp);
for (j = 0; j < i; j++)
{
newenv[j] = strdup (wsp->ws_env[j]);
if (!newenv[j])
{
for (; j > 1; j--)
free (newenv[j-1]);
free (newenv[j-1]);
return _wsplt_nomem (wsp);
}
}
newenv[j] = NULL;
wsp->ws_envbuf = newenv;
wsp->ws_envidx = i;
wsp->ws_envsiz = sz;
wsp->ws_env = (const char**) wsp->ws_envbuf;
}
else
{
newenv = calloc (WORDSPLIT_ENV_INIT, sizeof(newenv[0]));
if (!newenv)
return _wsplt_nomem (wsp);
wsp->ws_envbuf = newenv;
wsp->ws_envidx = 0;
wsp->ws_envsiz = WORDSPLIT_ENV_INIT;
wsp->ws_env = (const char**) wsp->ws_envbuf;
wsp->ws_flags |= WRDSF_ENV;
}
}
else
{
wsp->ws_envsiz *= 2;
newenv = realloc (wsp->ws_envbuf,
wsp->ws_envsiz * sizeof (wsp->ws_envbuf[0]));
if (!newenv)
return _wsplt_nomem (wsp);
wsp->ws_envbuf = newenv;
wsp->ws_env = (const char**) wsp->ws_envbuf;
}
}
if (wsp->ws_flags & WRDSF_ENV_KV)
{
/* A key-value pair environment */
char *p = malloc (namelen + 1);
if (!p)
return _wsplt_nomem (wsp);
memcpy (p, name, namelen);
p[namelen] = 0;
v = strdup (value);
if (!v)
{
free (p);
return _wsplt_nomem (wsp);
}
wsp->ws_env[wsp->ws_envidx++] = p;
wsp->ws_env[wsp->ws_envidx++] = v;
}
else
{
v = malloc (namelen + strlen(value) + 2);
if (!v)
return _wsplt_nomem (wsp);
memcpy (v, name, namelen);
v[namelen++] = '=';
strcpy(v + namelen, value);
wsp->ws_env[wsp->ws_envidx++] = v;
}
wsp->ws_env[wsp->ws_envidx++] = NULL;
return WRDSE_OK;
}
static int
@ -767,7 +899,9 @@ expvar (struct wordsplit *wsp, const char *str, size_t len,
const char *vptr;
struct wordsplit_node *newnode;
const char *start = str - 1;
int rc;
struct wordsplit ws;
if (ISVARBEG (str[0]))
{
for (i = 1; i < len; i++)
@ -780,22 +914,35 @@ expvar (struct wordsplit *wsp, const char *str, size_t len,
str++;
len--;
for (i = 1; i < len; i++)
if (str[i] == '}' || str[i] == ':')
break;
if (str[i] == ':')
{
size_t j;
defstr = str + i + 1;
if (find_closing_paren (str, i + 1, len, &j, "{}"))
return _wsplt_seterr (wsp, WRDSE_CBRACE);
*pend = str + j;
if (str[i] == ':')
{
size_t j;
defstr = str + i + 1;
if (find_closing_paren (str, i + 1, len, &j, "{}"))
return _wsplt_seterr (wsp, WRDSE_CBRACE);
*pend = str + j;
break;
}
else if (str[i] == '}')
{
defstr = NULL;
*pend = str + i;
break;
}
else if (strchr ("-+?=", str[i]))
{
size_t j;
defstr = str + i;
if (find_closing_paren (str, i, len, &j, "{}"))
return _wsplt_seterr (wsp, WRDSE_CBRACE);
*pend = str + j;
break;
}
}
else if (str[i] == '}')
{
*pend = str + i;
}
else
if (i == len)
return _wsplt_seterr (wsp, WRDSE_CBRACE);
}
else
@ -820,64 +967,99 @@ expvar (struct wordsplit *wsp, const char *str, size_t len,
i - its length
defstr - default replacement str */
vptr = wordsplit_find_env (wsp, str, i);
if (vptr)
if (defstr && strchr("-+?=", defstr[0]) == 0)
{
value = strdup (vptr);
if (!value)
return _wsplt_nomem (wsp);
}
else if (wsp->ws_flags & WRDSF_GETVAR)
{
int rc = wsp->ws_getvar (&value, str, i, wsp->ws_closure);
switch (rc)
{
case WRDSE_OK:
break;
case WRDSE_NOSPACE:
return _wsplt_nomem (wsp);
case WRDSE_UNDEF:
value = NULL;
break;
case WRDSE_USERERR:
if (wsp->ws_errno == WRDSE_USERERR)
free (wsp->ws_usererr);
wsp->ws_usererr = value;
/* fall through */
default:
_wsplt_seterr (wsp, rc);
return 1;
}
rc = WRDSE_UNDEF;
defstr = NULL;
}
else
value = NULL;
if (!value)
{
rc = wordsplit_find_env (wsp, str, i, &vptr);
if (rc == WRDSE_OK)
{
value = strdup (vptr);
if (!value)
rc = WRDSE_NOSPACE;
}
else if (wsp->ws_flags & WRDSF_GETVAR)
rc = wsp->ws_getvar (&value, str, i, wsp->ws_closure);
else
rc = WRDSE_UNDEF;
if (rc == WRDSE_OK && value[0] == 0 && defstr && defstr[-1] == ':')
{
free (value);
rc = WRDSE_UNDEF;
}
}
switch (rc)
{
case WRDSE_OK:
if (defstr && *defstr == '+')
{
size_t size = *pend - ++defstr;
rc = _wsplt_subsplit (wsp, &ws, defstr, size,
WRDSF_NOSPLIT | WRDSF_WS | WRDSF_QUOTE |
(wsp->ws_flags &
(WRDSF_NOVAR | WRDSF_NOCMD)));
if (rc)
return rc;
free (value);
value = ws.ws_wordv[0];
ws.ws_wordv[0] = NULL;
wordsplit_free (&ws);
}
break;
case WRDSE_UNDEF:
if (defstr)
{
size_t size;
if (*defstr == '-')
if (*defstr == '-' || *defstr == '=')
{
size = *pend - ++defstr;
value = malloc (size + 1);
if (!value)
return _wsplt_nomem (wsp);
memcpy (value, defstr, size);
value[size] = 0;
rc = _wsplt_subsplit (wsp, &ws, defstr, size,
WRDSF_NOSPLIT | WRDSF_WS | WRDSF_QUOTE |
(wsp->ws_flags &
(WRDSF_NOVAR | WRDSF_NOCMD)));
if (rc)
return rc;
value = ws.ws_wordv[0];
ws.ws_wordv[0] = NULL;
wordsplit_free (&ws);
if (defstr[-1] == '=')
wsplt_assign_var (wsp, str, i, value);
}
else if (*defstr == '?')
else
{
size = *pend - ++defstr;
if (size == 0)
wsp->ws_error (_("%.*s: variable null or not set"),
(int) i, str);
else
wsp->ws_error ("%.*s: %.*s",
(int) i, str, (int) size, defstr);
if (*defstr == '?')
{
size = *pend - ++defstr;
if (size == 0)
wsp->ws_error (_("%.*s: variable null or not set"),
(int) i, str);
else
{
rc = _wsplt_subsplit (wsp, &ws, defstr, size,
WRDSF_NOSPLIT | WRDSF_WS |
WRDSF_QUOTE |
(wsp->ws_flags &
(WRDSF_NOVAR | WRDSF_NOCMD)));
if (rc == 0)
wsp->ws_error ("%.*s: %s",
(int) i, str, ws.ws_wordv[0]);
else
wsp->ws_error (_("%.*s: %.*s"),
(int) i, str, (int) size, defstr);
wordsplit_free (&ws);
}
}
value = NULL;
}
}
else if (wsp->ws_flags & WRDSF_UNDEF)
@ -899,18 +1081,21 @@ expvar (struct wordsplit *wsp, const char *str, size_t len,
return _wsplt_nomem (wsp);
}
}
break;
case WRDSE_NOSPACE:
return _wsplt_nomem (wsp);
case WRDSE_USERERR:
if (wsp->ws_errno == WRDSE_USERERR)
free (wsp->ws_usererr);
wsp->ws_usererr = value;
/* fall through */
default:
_wsplt_seterr (wsp, rc);
return 1;
}
else if (defstr && *defstr == '+')
{
size_t size = *pend - ++defstr;
free (value);
value = malloc (size + 1);
if (!value)
return _wsplt_nomem (wsp);
memcpy (value, defstr, size);
value[size] = 0;
}
if (value)
{
if (flg & _WSNF_QUOTE)
@ -1111,7 +1296,7 @@ expcmd (struct wordsplit *wsp, const char *str, size_t len,
}
*pend = str + j;
if (wsp->ws_flags & WRDSF_ARGV)
if (wsp->ws_options & WRDSO_ARGV)
{
struct wordsplit ws;
@ -2033,6 +2218,23 @@ wordsplit_free_words (struct wordsplit *ws)
ws->ws_wordc = 0;
}
void
wordsplit_free_envbuf (struct wordsplit *ws)
{
if (ws->ws_flags & WRDSF_NOCMD)
return;
if (ws->ws_envbuf)
{
size_t i;
for (i = 0; ws->ws_envbuf[i]; i++)
free (ws->ws_envbuf[i]);
free (ws->ws_envbuf);
ws->ws_envidx = ws->ws_envsiz = 0;
ws->ws_envbuf = NULL;
}
}
void
wordsplit_clearerr (struct wordsplit *ws)
{
@ -2048,6 +2250,7 @@ wordsplit_free (struct wordsplit *ws)
wordsplit_free_words (ws);
free (ws->ws_wordv);
ws->ws_wordv = NULL;
wordsplit_free_envbuf (ws);
}
const char *_wordsplit_errstr[] = {

37
src/wordsplit.h
View file

@ -19,6 +19,8 @@
#include <stddef.h>
typedef struct wordsplit wordsplit_t;
/* Structure used to direct the splitting. Members marked with [Input]
can be defined before calling wordsplit(), those marked with [Output]
provide return values when the function returns. If neither mark is
@ -43,7 +45,7 @@ struct wordsplit
const char *ws_comment; /* [Input] (WRDSF_COMMENT) Comment characters. */
const char *ws_escape; /* [Input] (WRDSF_ESCAPE) Characters to be escaped
with backslash. */
void (*ws_alloc_die) (struct wordsplit *wsp);
void (*ws_alloc_die) (wordsplit_t *wsp);
/* [Input] (WRDSF_ALLOC_DIE) Function called when
out of memory. Must not return. */
void (*ws_error) (const char *, ...)
@ -56,6 +58,11 @@ struct wordsplit
output. */
const char **ws_env; /* [Input] (WRDSF_ENV, !WRDSF_NOVAR) Array of
environment variables. */
char **ws_envbuf;
size_t ws_envidx;
size_t ws_envsiz;
int (*ws_getvar) (char **ret, const char *var, size_t len, void *clos);
/* [Input] (WRDSF_GETVAR, !WRDSF_NOVAR) Looks up
the name VAR (LEN bytes long) in the table of
@ -86,7 +93,7 @@ struct wordsplit
size_t ws_endp; /* Points past the last processed byte in
ws_input. */
int ws_errno; /* [Output] Error code, if an error occurred. */
char *ws_usererr; /* [Input/Output] Points to textual description of
char *ws_usererr; /* Points to textual description of
the error, if ws_errno is WRDSE_USERERR. Must
be allocated with malloc(3). */
struct wordsplit_node *ws_head, *ws_tail;
@ -94,6 +101,9 @@ struct wordsplit
int ws_lvl; /* Invocation nesting level. */
};
/* Initial size for ws_env, if allocated automatically */
#define WORDSPLIT_ENV_INIT 16
/* Wordsplit flags. */
/* Append the words found to the array resulting from a previous
call. */
@ -164,10 +174,10 @@ struct wordsplit
#define WRDSF_ESCAPE 0x10000000
/* Incremental mode */
#define WRDSF_INCREMENTAL 0x20000000
/* ws_command needs argv parameter */
#define WRDSF_ARGV 0x40000000
/* Perform pathname and tilde expansion */
#define WRDSF_PATHEXPAND 0x80000000
#define WRDSF_PATHEXPAND 0x40000000
/* ws_options is initialized */
#define WRDSF_OPTIONS 0x80000000
#define WRDSF_DEFFLAGS \
(WRDSF_NOVAR | WRDSF_NOCMD | \
@ -179,6 +189,8 @@ struct wordsplit
#define WRDSO_FAILGLOB 0x02
/* Allow a leading period to be matched by metacharacters. */
#define WRDSO_DOTGLOB 0x04
/* ws_command needs argv parameter */
#define WRDSO_ARGV 0x08
#define WRDSE_OK 0
#define WRDSE_EOF WRDSE_OK
@ -192,11 +204,12 @@ struct wordsplit
#define WRDSE_GLOBERR 8
#define WRDSE_USERERR 9
int wordsplit (const char *s, struct wordsplit *p, int flags);
int wordsplit (const char *s, wordsplit_t *p, int flags);
int wordsplit_len (const char *s, size_t len,
struct wordsplit *p, int flags);
void wordsplit_free (struct wordsplit *p);
void wordsplit_free_words (struct wordsplit *ws);
wordsplit_t *p, int flags);
void wordsplit_free (wordsplit_t *p);
void wordsplit_free_words (wordsplit_t *ws);
void wordsplit_free_envbuf (struct wordsplit *ws);
int wordsplit_c_unquote_char (int c);
int wordsplit_c_quote_char (int c);
@ -208,9 +221,9 @@ void wordsplit_sh_unquote_copy (char *dst, const char *src, size_t n);
void wordsplit_c_unquote_copy (char *dst, const char *src, size_t n);
void wordsplit_c_quote_copy (char *dst, const char *src, int quote_hex);
void wordsplit_perror (struct wordsplit *ws);
const char *wordsplit_strerror (struct wordsplit *ws);
void wordsplit_perror (wordsplit_t *ws);
const char *wordsplit_strerror (wordsplit_t *ws);
void wordsplit_clearerr (struct wordsplit *ws);
void wordsplit_clearerr (wordsplit_t *ws);
#endif

41
tests/wordsplit.at
View file

@ -452,6 +452,47 @@ TESTWSP([default value],[wsp-var wsp-var14 wsp40],[],
0: bar
])
TESTWSP([default value (defined)],[wsp-var wsp-var13 wsp39],[],
[${FOO:-bar}],
[NF: 1
0: qux
],
[],
[FOO=qux])
# FIXME: breaks wspN numbering
TESTWSP([default value (:- null)],[wsp-var],[],
[${FOO:-bar}],
[NF: 1
0: bar
],
[],
[FOO=])
TESTWSP([default value (- null)],[wsp-var],[],
[${FOO-bar}],
[NF: 0
],
[],
[FOO=])
TESTWSP([default value (- null, unset)],[wsp-var],[],
[${FOO-bar}],
[NF: 1
0: bar
])
TESTWSP([assign default values],[wsp-var],[],
[${FOO=bar}
$FOO],
[NF: 1
0: bar
NF: 1
0: bar
])
# FIXME ends here
TESTWSP([default error message (var defined)],[wsp-var wsp-var15 wsp41],[],
[a ${FOO:?} test],
[NF: 3

76
tests/wsp.c
View file

@ -95,6 +95,8 @@ help ()
printf ("options are:\n");
printf (" [-]trimnl\n");
printf (" [-]plaintext\n");
printf (" -env\n");
printf (" env sys|none|null\n");
putchar ('\n');
for (i = 0; bool_keytab[i].name; i++)
printf (" [-]%s\n", bool_keytab[i].name);
@ -265,6 +267,20 @@ wsp_runcmd (char **ret, const char *str, size_t len, char **argv, void *closure)
return WRDSE_OK;
}
enum env_type
{
env_none,
env_null,
env_sys
};
struct kwd env_keytab[] = {
{ "none", env_none },
{ "null", env_null },
{ "sys", env_sys },
{ NULL }
};
int
main (int argc, char **argv)
{
@ -274,12 +290,13 @@ main (int argc, char **argv)
int plaintext_option = 0;
int wsflags = (WRDSF_DEFFLAGS & ~WRDSF_NOVAR) |
WRDSF_ENOMEMABRT |
WRDSF_ENV | WRDSF_SHOWERR;
struct wordsplit ws;
WRDSF_SHOWERR;
wordsplit_t ws;
int next_call = 0;
char *fenvbase[128];
size_t fenvidx = 0;
size_t fenvmax = sizeof (fenvbase) / sizeof (fenvbase[0]);
int use_env = env_sys;
progname = argv[0];
@ -321,7 +338,31 @@ main (int argc, char **argv)
plaintext_option = !negate;
continue;
}
if (strcmp (opt, "env") == 0)
{
if (negate)
use_env = env_none;
else
{
i++;
if (i == argc)
{
fprintf (stderr, "%s: missing argument for env\n",
progname);
exit (1);
}
if (kwxlat (env_keytab, argv[i], &use_env))
{
fprintf (stderr, "%s: invalid argument for env\n",
progname);
exit (1);
}
}
continue;
}
if (kwxlat (bool_keytab, opt, &flag) == 0)
{
if (negate)
@ -405,6 +446,7 @@ main (int argc, char **argv)
if (kwxlat (opt_keytab, opt, &flag) == 0)
{
wsflags |= WRDSF_OPTIONS;
if (negate)
ws.ws_options &= ~flag;
else
@ -431,12 +473,26 @@ main (int argc, char **argv)
ws.ws_getvar = wsp_getvar;
ws.ws_closure = fenvbase;
}
if (wsflags & WRDSF_ENV_KV)
ws.ws_env = (const char **) make_env_kv ();
else
ws.ws_env = (const char **) environ;
switch (use_env)
{
case env_null:
wsflags |= WRDSF_ENV;
ws.ws_env = NULL;
break;
case env_none:
break;
case env_sys:
wsflags |= WRDSF_ENV;
if (wsflags & WRDSF_ENV_KV)
ws.ws_env = (const char **) make_env_kv ();
else
ws.ws_env = (const char **) environ;
break;
}
if (!(wsflags & WRDSF_NOCMD))
ws.ws_command = wsp_runcmd;
@ -488,8 +544,8 @@ main (int argc, char **argv)
ws.ws_wordv[i] = argv[offarg + i];
offarg = 0;
}
wsflags |= WRDSF_REUSE;
wsflags |= WRDSF_REUSE | (ws.ws_flags & WRDSF_ENV);
printf ("NF: %lu", (unsigned long) ws.ws_wordc);
if (wsflags & WRDSF_DOOFFS)
printf (" (%lu)", (unsigned long) ws.ws_offs);