added win32 nwio
This commit is contained in:
@ -1,14 +1,26 @@
|
||||
/** @page awk AWK
|
||||
|
||||
@section awk_content CONTENTS
|
||||
- @ref awk_intro "INTRODUCTION"
|
||||
- @ref awk_lang "AWK LANGUAGE"
|
||||
- @ref awk_ext "AWK LANGUAGE EXTENSIONS"
|
||||
- @ref awk_ext_vardecl " VARIABLE DECLARATION"
|
||||
- @ref awk_ext_include "INCLUDE"
|
||||
- @ref awk_ext_rwpipe "TWO-WAY PIPE"
|
||||
- @ref awk_ext_return "RETURN"
|
||||
- @ref awk_ext_comment "COMMENT"
|
||||
- @ref awk_ext_fnc "EXTENDED FUNCTIONS"
|
||||
- @ref awk_ext_fs "EXTENDED FS"
|
||||
- @ref awk_ext_binnum "BINARY NUMBER"
|
||||
- @ref awk_ext_unicode "UNICODE ESCAPE SEQUENCE"
|
||||
- @ref awk_ext_ioenc "I/O ENCODING"
|
||||
|
||||
|
||||
@section awk_intro INTRODUCTION
|
||||
|
||||
QSEAWK is an embeddable AWK interpreter and is a part of the @ref qse_intro
|
||||
"QSE" library. The interpreter implements the language described in the book
|
||||
<a class="el" href="http://cm.bell-labs.com/cm/cs/awkbook/">
|
||||
The AWK Proramming Language</a>
|
||||
with @ref awk_ext "extensions". Its design focuses on building a flexible
|
||||
and robust embedding API with minimal platform dependency. An embedding
|
||||
application is capable of
|
||||
"QSE" library. Its design focuses on building a flexible and robust embedding
|
||||
API with minimal platform dependency. An embedding application is capable of
|
||||
- adding new global variables and functions.
|
||||
- getting and set the value of a global variable.
|
||||
- calling a function with or without parameters and getting its return value.
|
||||
@ -39,40 +51,42 @@ The code example below demonstrates the steps in C. It executes the one liner
|
||||
|
||||
int main ()
|
||||
{
|
||||
qse_awk_t* awk = QSE_NULL;
|
||||
qse_awk_rtx_t* rtx = QSE_NULL;
|
||||
qse_awk_val_t* retv;
|
||||
qse_awk_parsestd_in_t psin;
|
||||
int ret = -1;
|
||||
qse_awk_t* awk = QSE_NULL;
|
||||
qse_awk_rtx_t* rtx = QSE_NULL;
|
||||
qse_awk_val_t* retv;
|
||||
qse_awk_parsestd_t psin;
|
||||
int ret = -1;
|
||||
|
||||
awk = qse_awk_openstd (0); /* open a new interpreter */
|
||||
if (!awk) FAIL ("cannot open awk");
|
||||
awk = qse_awk_openstd (0); /* open a new interpreter */
|
||||
if (!awk) FAIL ("cannot open awk");
|
||||
|
||||
/* parse the hello world script from a string */
|
||||
psin.type = QSE_AWK_PARSESTD_CP;
|
||||
psin.u.cp = QSE_T("BEGIN { print \"hello, world\" }");
|
||||
if (qse_awk_parsestd (awk, &psin, QSE_NULL) <= -1)
|
||||
FAIL (qse_awk_geterrmsg(awk));
|
||||
/* parse the hello world script from a string */
|
||||
psin.type = QSE_AWK_PARSESTD_STR;
|
||||
psin.u.str.ptr = QSE_T("BEGIN { print \"hello, world\" }");
|
||||
psin.u.str.len = qse_strlen(psin.u.str.ptr);
|
||||
if (qse_awk_parsestd (awk, &psin, QSE_NULL) <= -1)
|
||||
FAIL (qse_awk_geterrmsg(awk));
|
||||
|
||||
rtx = qse_awk_rtx_openstd ( /* open a runtime context */
|
||||
awk, 0, /* no extension */
|
||||
QSE_T("hello"), /* ARGV[0] */
|
||||
QSE_NULL, /* stdin */
|
||||
QSE_NULL /* stdout */
|
||||
);
|
||||
if (!rtx) FAIL (qse_awk_geterrmsg(awk));
|
||||
rtx = qse_awk_rtx_openstd ( /* open a runtime context */
|
||||
awk, 0, /* no extension */
|
||||
QSE_T("hello"), /* ARGV[0] */
|
||||
QSE_NULL, /* stdin */
|
||||
QSE_NULL, /* stdout */
|
||||
QSE_NULL /* default cmgr */
|
||||
);
|
||||
if (!rtx) FAIL (qse_awk_geterrmsg(awk));
|
||||
|
||||
/* exeucte BEGIN,pattern-action,END blocks */
|
||||
retv = qse_awk_rtx_loop (rtx);
|
||||
if (!retv) FAIL (qse_awk_rtx_geterrmsg(rtx));
|
||||
/* exeucte BEGIN,pattern-action,END blocks */
|
||||
retv = qse_awk_rtx_loop (rtx);
|
||||
if (!retv) FAIL (qse_awk_rtx_geterrmsg(rtx));
|
||||
|
||||
qse_awk_rtx_refdownval (rtx, retv); /* destroy the return value */
|
||||
ret = 0;
|
||||
qse_awk_rtx_refdownval (rtx, retv); /* destroy the return value */
|
||||
ret = 0;
|
||||
|
||||
oops:
|
||||
if (rtx) qse_awk_rtx_close (rtx); /* close the runtime context */
|
||||
if (awk) qse_awk_close (awk); /* close the interpreter */
|
||||
return ret;
|
||||
if (rtx) qse_awk_rtx_close (rtx); /* close the runtime context */
|
||||
if (awk) qse_awk_close (awk); /* close the interpreter */
|
||||
return ret;
|
||||
}
|
||||
@endcode
|
||||
|
||||
@ -119,9 +133,63 @@ int main (int argc, char* argv[])
|
||||
}
|
||||
@endcode
|
||||
|
||||
@section awk_ext EXTENSIONS
|
||||
Some language extensions are implemented and they can be enabled by setting the
|
||||
corresponding options.
|
||||
This library also provides a stand-alone AWK interpreter that you can use
|
||||
in a console environment. The source code is located under the
|
||||
<project-root>/cmd/awk subdirectory.
|
||||
|
||||
@code
|
||||
$ qseawk
|
||||
USAGE: qseawk [options] -f sourcefile [ -- ] [datafile]*
|
||||
qseawk [options] [ -- ] sourcestring [datafile]*
|
||||
Where options are:
|
||||
-h/--help print this message
|
||||
--version print version
|
||||
-D show extra information
|
||||
-c/--call name call a function instead of entering
|
||||
the pattern-action loop
|
||||
-f/--file sourcefile set the source script file
|
||||
-d/--deparsed-file deparsedfile set the deparsing output file
|
||||
-F/--field-separator string set a field separator(FS)
|
||||
-v/--assign var=value add a global variable with a value
|
||||
-m/--memory-limit number limit the memory usage (bytes)
|
||||
-X number fail the number'th memory allocation
|
||||
--script-encoding string specify script file encoding name
|
||||
--console-encoding string specify console encoding name
|
||||
--implicit on/off allow undeclared variables
|
||||
--explicit on/off allow declared variables(local,global)
|
||||
--extraops on/off enable extra operators(<<,>>,^^,\)
|
||||
--rio on/off enable builtin I/O including getline & print
|
||||
--rwpipe on/off allow a dual-directional pipe
|
||||
--newline on/off enable a newline to terminate a statement
|
||||
--striprecspc on/off strip spaces in splitting a record
|
||||
--stripstrspc on/off strip spaces in converting a string to a number
|
||||
--nextofile on/off enable 'nextofile'
|
||||
--reset on/off enable 'reset'
|
||||
--crlf on/off use CRLF for a newline
|
||||
--maptovar on/off allow a map to be assigned or returned
|
||||
--pablock on/off enable pattern-action loop
|
||||
--rexbound on/off enable {n,m} in a regular expression
|
||||
--ncmponstr on/off perform numeric comparsion on numeric strings
|
||||
--strictnaming on/off enable the strict naming rule
|
||||
--include on/off enable 'include'
|
||||
@endcode
|
||||
|
||||
@section awk_lang AWK LANGUAGE
|
||||
QSEAWK implements the language described in the book
|
||||
<a class="el" href="http://cm.bell-labs.com/cm/cs/awkbook/">
|
||||
The AWK Proramming Language</a> with various @ref awk_ext "extensions".
|
||||
|
||||
- BEGIN block
|
||||
- END block
|
||||
- Pattern-action block
|
||||
- User-defined functions
|
||||
- Expressions
|
||||
- Statements
|
||||
- Streams
|
||||
|
||||
@section awk_ext AWK LANGUAGE EXTENSIONS
|
||||
Some language extensions are implemented and those can be enabled by setting
|
||||
the corresponding options.
|
||||
|
||||
@subsection awk_ext_vardecl VARIABLE DECLARATION
|
||||
|
||||
@ -186,6 +254,29 @@ BEGIN {
|
||||
}
|
||||
@endcode
|
||||
|
||||
This two-way pipe can create a TCP or UDP connection if the pipe command
|
||||
string is prefixed with one of the followings:
|
||||
|
||||
- tcp:// - establishes a TCP connection to a specified IP address/port.
|
||||
- udp:// - establishes a TCP connection to a specified IP address/port.
|
||||
- tcpd:// - binds a TCP socket to a specified IP address/port and waits for the first connection.
|
||||
- udpd:// - binds a TCP socket to a specified IP address/port and waits for the first sender.
|
||||
|
||||
@code
|
||||
BEGIN {
|
||||
# it binds a TCP socket to the IPv6 address :: and the port number
|
||||
# 9999 and waits for the first coming connection. It repeats writing
|
||||
# "hello world" to the first connected peer and reading a line from
|
||||
# it until the session is torn down.
|
||||
do {
|
||||
print "hello world" || "tcpd://[::]:9999";
|
||||
if (("tcpd://[::]:9999" || getline x) <= 0) break;
|
||||
print x;
|
||||
}
|
||||
while(1);
|
||||
}
|
||||
@endcode
|
||||
|
||||
@subsection awk_ext_return RETURN
|
||||
The return statement is valid in BEGIN blocks, END blocks, and pattern-action
|
||||
blocks as well as in functions. The execution of a calling block is aborted
|
||||
@ -232,24 +323,123 @@ BEGIN {
|
||||
@endcode
|
||||
|
||||
@subsection awk_ext_fs EXTENDED FS
|
||||
|
||||
If the value for FS begins with a question mark followed by 4
|
||||
additional letters, QSEAWK can split a record with quoted fields
|
||||
delimited by a single-letter separator.
|
||||
|
||||
The 4 additional letters are composed of a field separator,
|
||||
an escaper, a opening quote, and a closing quote.
|
||||
|
||||
@code
|
||||
BEGIN { FS="?:\\\"\""; }
|
||||
$ cat x.awk
|
||||
BEGIN { FS="?:\\[]"; }
|
||||
{
|
||||
for (i = 1; i <= NF; i++)
|
||||
print "$" i ": " $i;
|
||||
print "---------------";
|
||||
}
|
||||
@endcode
|
||||
|
||||
The value of FS above means the following.
|
||||
- : is a field separator.
|
||||
- a backslash is an escaper.
|
||||
- a left bracket is an opening quote.
|
||||
- a right bracket is a closing quote.
|
||||
|
||||
See the following output.
|
||||
@code
|
||||
$ cat x.dat
|
||||
[fx1]:[fx2]:[f\[x\]3]
|
||||
abc:def:[a b c]
|
||||
$ qseawk -f x.awk x.dat
|
||||
$1: fx1
|
||||
$2: fx2
|
||||
$3: f[x]3
|
||||
---------------
|
||||
$1: abc
|
||||
$2: def
|
||||
$3: a b c
|
||||
---------------
|
||||
@endcode
|
||||
|
||||
|
||||
|
||||
@subsection awk_ext_binnum BINARY NUMBER
|
||||
Use 0b to begin a binary number sequence.
|
||||
|
||||
@code
|
||||
BEGIN { print 0b1101; }
|
||||
$ qseawk 'BEGIN { printf ("%b %o %d %x\n", 0b1101, 0b1101, 0b1101, 0b1101); }'
|
||||
1101 15 13 d
|
||||
@endcode
|
||||
|
||||
|
||||
|
||||
@subsection awk_ext_unicode UNICODE ESCAPE SEQUENCE
|
||||
|
||||
If QSE is compiled for #QSE_CHAR_IS_WCHAR, you can use \\u and \\U in a
|
||||
string to specify a character by unicode.
|
||||
|
||||
@code
|
||||
BEGIN { print "string=>[\uB313\U0000B313]"; }
|
||||
$ qseawk 'BEGIN { print "\uC720\uB2C8\uCF54\uB4DC \U00007D71\U00004E00\U000078BC"; }'
|
||||
유니코드 統一碼
|
||||
@endcode
|
||||
|
||||
|
||||
@subsection awk_ext_ioenc I/O ENCODING
|
||||
You can call setenc() to set the character encoding of a stream resource like
|
||||
a pipe or a file. See qse_findcmgr() for a list of supported encoding names.
|
||||
|
||||
Let's say you run this simple echoing script on a WIN32 platform that has
|
||||
the active code page of 949 and is reachable at the IP address 192.168.2.8.
|
||||
|
||||
@code
|
||||
C:\> chcp
|
||||
Active code page: 949
|
||||
C:\> type s.awk
|
||||
BEGIN {
|
||||
sock = "tcpd://0.0.0.0:9999";
|
||||
setenc (sock, "cp949"); # this is not needed since the active
|
||||
# code page is already 949.
|
||||
do {
|
||||
|
||||
if ((sock || getline x) <= 0) break;
|
||||
print "PEER: " x;
|
||||
print x || sock;
|
||||
}
|
||||
while(1);
|
||||
}
|
||||
C:\> qseawk --rwpipe=on -f r.awk
|
||||
PEER: 안녕
|
||||
PEER: ?好!
|
||||
@endcode
|
||||
|
||||
Now you run the following script on a UTF-8 console of a Linux box.
|
||||
|
||||
@code
|
||||
$ echo $LANG
|
||||
en_US.UTF-8
|
||||
$ cat c.awk
|
||||
BEGIN {
|
||||
peer = "tcp://192.168.2.8:9999";
|
||||
setenc (peer, "cp949");
|
||||
do
|
||||
{
|
||||
printf "> ";
|
||||
if ((getline x) <= 0) break;
|
||||
print x || peer;
|
||||
if ((peer || getline line) <= -1) break;
|
||||
print "PEER: " line;
|
||||
}
|
||||
while (1);
|
||||
}
|
||||
$ qseawk --rwpipe=on -f c.awk
|
||||
> 안녕
|
||||
PEER: 안녕
|
||||
> 你好!
|
||||
PEER: ?好!
|
||||
@endcode
|
||||
|
||||
Note that 你 has been converted to a question mark since the letter is
|
||||
not supported by cp949.
|
||||
*/
|
||||
|
||||
@ -4,5 +4,5 @@
|
||||
- Generic text stream interface #qse_tio_t
|
||||
- Simple text stream over a file #qse_sio_t
|
||||
- Pipe stream to/from a process #qse_pio_t
|
||||
|
||||
- Network stream to/from a remote/local host #qse_nwio_t
|
||||
*/
|
||||
|
||||
Reference in New Issue
Block a user