fixed witdth flag ! added
This commit is contained in:
249
doc/formats.html
249
doc/formats.html
@ -28,8 +28,8 @@ A format converter consists of
|
||||
</p>
|
||||
<ul>
|
||||
<li>The <code>%</code> character</li>
|
||||
<li>Optionally a field <span class="new">or record</span> name in <code>()</code></li>
|
||||
<li>Optionally flags out of the characters <code>*# +0-<span class="new">?=</span></code></li>
|
||||
<li>Optionally a field or record name in <code>()</code></li>
|
||||
<li>Optionally flags out of the characters <code>*# +0-?=!</code></li>
|
||||
<li>Optionally an integer <em>width</em> field</li>
|
||||
<li>Optionally a period character (<code>.</code>) followed
|
||||
by an integer <em>precision</em> field (input ony for most formats)</li>
|
||||
@ -40,7 +40,7 @@ A format converter consists of
|
||||
<p>
|
||||
The flags <code>*# +0-</code> work like in the C functions
|
||||
<em>printf()</em> and <em>scanf()</em>.
|
||||
The flags <code>?</code> and <code>=</code> are extensions.
|
||||
The flags <code>?</code>, <code>=</code> and <code>!</code> are extensions.
|
||||
</p>
|
||||
<p>
|
||||
The <code>*</code> flag skips data in input formats.
|
||||
@ -67,16 +67,24 @@ The <code>0</code> flag says that numbers should be left padded with
|
||||
The <code>-</code> flag specifies that output is left justified if
|
||||
<em>width</em> is larger than required.
|
||||
</p>
|
||||
<p class="new">
|
||||
<p>
|
||||
The <code>?</code> flag makes failing input conversions succeed with
|
||||
a default zero value (0, 0.0, or "", depending on the format type).
|
||||
</p>
|
||||
<p class="new">
|
||||
<p>
|
||||
The <code>=</code> flag allows to compare input with current values.
|
||||
It is only allowed in input formats.
|
||||
Instead of reading a new value from input, the current value is
|
||||
formatted (like for output) and then compared to the input.
|
||||
</p>
|
||||
<p>
|
||||
The <code>!</code> flag demands that input is exactly <em>width</em>
|
||||
bytes long (normally <em>width</em> defines the maximum number of
|
||||
bytes read in many formats).
|
||||
For example <code>in "%!5d";</code> expects exactly 5 digits.
|
||||
Fewer digits are considered loss of data and make the format fail.
|
||||
This feature has been added by Klemen Vodopivec, SNS.
|
||||
</p>
|
||||
|
||||
<h3>Examples:</h3>
|
||||
<table>
|
||||
@ -143,11 +151,8 @@ field formatted as a string.
|
||||
Use <code>in "%(<i>otherrecord</i>.RVAL)f";</code> to write the floating
|
||||
point input value into the <code>RVAL</code> field of
|
||||
<code><i>otherrecord</i></code>.
|
||||
<span class="new">
|
||||
If no field is given for an other record .VAL is assumed.
|
||||
When a record name conflicts with a field name use .VAL explicitly.
|
||||
</span>
|
||||
|
||||
</p>
|
||||
<p>
|
||||
This feature is very useful when one line of input contains many values that should
|
||||
@ -158,7 +163,7 @@ attribute (see
|
||||
target="ex">Record Reference Manual</a>), the record will be processed.
|
||||
It is your responsibility that the data type of the record field is
|
||||
compatible to the the data type of the converter.
|
||||
<span class="new">STRING formats are compatible with arrays of CHAR or UCHAR.<span>
|
||||
STRING formats are compatible with arrays of CHAR or UCHAR.
|
||||
</p>
|
||||
<p>
|
||||
Note that using this syntax is by far not as efficient as using the
|
||||
@ -192,11 +197,11 @@ With the <code>#</code> flag, output always contains a period character.
|
||||
<p>
|
||||
<b>Input:</b> All these formats are equivalent. Leading whitespaces are skipped.
|
||||
</p>
|
||||
<p class="new">
|
||||
<p>
|
||||
With the <code>#</code> flag additional whitespace between sign and number
|
||||
is accepted.
|
||||
</p>
|
||||
<p class="new">
|
||||
<p>
|
||||
When a maximum field width is given, leading whitespace only counts to the
|
||||
field witdth when the space flag is used.
|
||||
</p>
|
||||
@ -213,7 +218,7 @@ field witdth when the space flag is used.
|
||||
<p>
|
||||
With the <code>#</code> flag, octal values are prefixed with <code>0</code>
|
||||
and hexadecimal values with <code>0x</code> or <code>0X</code>.
|
||||
<p class="new">
|
||||
<p>
|
||||
Unlike printf, <code>%x</code> and <code>%X</code> truncate the
|
||||
output to the the given width (number of least significant half bytes).
|
||||
</p>
|
||||
@ -228,14 +233,14 @@ Octal and hexadecimal values can optionally be prefixed.
|
||||
hexadecimal notation.
|
||||
Leading whitespaces are skipped.
|
||||
</p>
|
||||
<p class="new">
|
||||
<p>
|
||||
With the <code>-</code> negative octal and hexadecimal values are accepted.
|
||||
</p>
|
||||
<p class="new">
|
||||
<p>
|
||||
With the <code>#</code> flag additional whitespace between sign and number
|
||||
is accepted.
|
||||
</p>
|
||||
<p class="new">
|
||||
<p>
|
||||
When a maximum field width is given, leading whitespace only counts to the
|
||||
field witdth when the space flag is used.
|
||||
</p>
|
||||
@ -253,13 +258,11 @@ and <code>%c</code> matches a sequence of not-null characters.
|
||||
The maximum string length is given by <em>width</em>.
|
||||
The default <em>width</em> is infinite for <code>%s</code> and
|
||||
1 for <code>%c</code>.
|
||||
Leading whitespaces are skipped with <code>%s</code>
|
||||
<span class="new">
|
||||
except when the space flag is used</span>
|
||||
but not with <code>%c</code>.
|
||||
Leading whitespaces are skipped with <code>%s</code> except when
|
||||
the space flag is used but not with <code>%c</code>.
|
||||
The empty string matches.
|
||||
</p>
|
||||
<p class="new">
|
||||
<p>
|
||||
With the <code>#</code> flag <code>%s</code> matches a sequence of not-null
|
||||
characters instead of non-whitespace characters.
|
||||
</p>
|
||||
@ -290,18 +293,18 @@ The strings are separated by <code>|</code>.
|
||||
Example: <code>%{OFF|STANDBY|ON}</code> mapps the string <code>OFF</code>
|
||||
to the value 0, <code>STANDBY</code> to 1 and <code>ON</code> to 2.
|
||||
</p>
|
||||
<p class="new">
|
||||
<p>
|
||||
When using the <code>#</code> flag it is allowed to assign integer values
|
||||
to the strings using <code>=</code>.
|
||||
Unassigned strings increment their values by 1 as usual.
|
||||
</p>
|
||||
<p class="new">
|
||||
<p>
|
||||
If one string is the initial substing of another, the substing must come
|
||||
later to ensure correct matching.
|
||||
In particular if one string is the emptry string, it must be the last one.
|
||||
Use <code>#</code> and <code>=</code> to renumber if necessary.
|
||||
</p>
|
||||
<p class="new">
|
||||
<p>
|
||||
Use the assignment <code>=?</code> for the last string to make it the
|
||||
default value for output formats.
|
||||
</p>
|
||||
@ -310,12 +313,12 @@ Example: <code>%#{neg=-1|stop|pos|fast=10|rewind=-10}</code>.
|
||||
</p>
|
||||
<p>
|
||||
If one of the strings contains <code>|</code> or <code>}</code>
|
||||
<span class="new">(or <code>=</code> if the <code>#</code> flag is used)</span>
|
||||
(or <code>=</code> if the <code>#</code> flag is used)
|
||||
a <code>\</code> must be used to escape the character.
|
||||
</p>
|
||||
<p>
|
||||
<b>Output:</b> Depending on the value, one of the strings is printed,
|
||||
<span class="new">or the default if no value matches</span>.
|
||||
or the default if no value matches.
|
||||
</p>
|
||||
<p>
|
||||
<b>Input:</b> If any of the strings matches, the value is set accordingly.
|
||||
@ -463,62 +466,158 @@ In input, the next byte or bytes must match the checksum.
|
||||
<h3>Implemented checksum functions</h3>
|
||||
<dl>
|
||||
<dt><code>%<sum></code> or <code>%<sum8></code></dt>
|
||||
<dd>One byte. The sum of all characters modulo 2<sup>8</sup>.</dd>
|
||||
<dd>
|
||||
The sum of all characters modulo 2<sup>8</sup>.
|
||||
<br>
|
||||
One byte. <code>123456789%<sum></code> = 0xdd
|
||||
</dd>
|
||||
<dt><code>%<sum16></code></dt>
|
||||
<dd>Two bytes. The sum of all characters modulo 2<sup>16</sup>.</dd>
|
||||
<dd>
|
||||
The sum of all characters modulo 2<sup>16</sup>.
|
||||
<br>
|
||||
Two bytes. <code>123456789%<sum16></code> = 0x01dd
|
||||
</dd>
|
||||
<dt><code>%<sum32></code></dt>
|
||||
<dd>Four bytes. The sum of all characters modulo 2<sup>32</sup>.</dd>
|
||||
<dd>
|
||||
The sum of all characters modulo 2<sup>32</sup>.
|
||||
<br>
|
||||
Four bytes. <code>123456789%<sum32></code> = 0x000001dd
|
||||
</dd>
|
||||
<dt><code>%<negsum></code>, <code>%<nsum></code>, <code>%<-sum></code>, <code>%<negsum8></code>, <code>%<nsum8></code>, or <code>%<-sum8></code></dt>
|
||||
<dd>One byte. The negative of the sum of all characters modulo 2<sup>8</sup>.</dd>
|
||||
<dd>
|
||||
The negative of the sum of all characters modulo 2<sup>8</sup>.
|
||||
<br>
|
||||
One byte. <code>123456789%<-sum8></code> = 0x23
|
||||
</dd>
|
||||
<dt><code>%<negsum16></code>, <code>%<nsum16></code>, or <code>%<-sum16></code></dt>
|
||||
<dd>Two bytes. The negative of the sum of all characters modulo 2<sup>16</sup>.</dd>
|
||||
<dd>
|
||||
The negative of the sum of all characters modulo 2<sup>16</sup>.
|
||||
<br>
|
||||
Two bytes. <code>123456789%<-sum16></code> = 0xfe23
|
||||
</dd>
|
||||
<dt><code>%<negsum32></code>, <code>%<nsum32></code>, or <code>%<-sum32></code></dt>
|
||||
<dd>Four bytes. The negative of the sum of all characters modulo 2<sup>32</sup>.</dd>
|
||||
<dd>
|
||||
The negative of the sum of all characters modulo 2<sup>32</sup>.
|
||||
<br>
|
||||
Four bytes. <code>123456789%<-sum32></code> = 0xfffffe23
|
||||
</dd>
|
||||
<dt><code>%<notsum></code> or <code>%<~sum></code></dt>
|
||||
<dd>One byte. The bitwise inverse of the sum of all characters modulo 2<sup>8</sup>.</dd>
|
||||
<dt><code>%<xor></code></dt>
|
||||
<dd>One byte. All characters xor'ed.</dd>
|
||||
<dt><code>%<xor7></code></dt>
|
||||
<dd>One byte. All characters xor'ed & 0x7F.</dd>
|
||||
<dt><code>%<crc8></code></dt>
|
||||
<dd>One byte. An often used 8 bit crc checksum
|
||||
(poly=0x07, init=0x00, xorout=0x00).</dd>
|
||||
<dt><code>%<ccitt8></code></dt>
|
||||
<dd>One byte. The CCITT standard 8 bit crc checksum
|
||||
(poly=0x31, init=0x00, xorout=0x00).</dd>
|
||||
<dt><code>%<crc16></code></dt>
|
||||
<dd>Two bytes. An often used 16 bit crc checksum
|
||||
(poly=0x8005, init=0x0000, xorout=0x0000).</dd>
|
||||
<dt><code>%<crc16r></code></dt>
|
||||
<dd>Two bytes. An often used reflected 16 bit crc checksum
|
||||
(poly=0x8005, init=0x0000, xorout=0x0000).</dd>
|
||||
<dt><code>%<ccitt16></code></dt>
|
||||
<dd>Two bytes. The usual (but <a target="ex"
|
||||
href="http://www.joegeluso.com/software/articles/ccitt.htm">wrong?</a>)
|
||||
implementation of the CCITT standard 16 bit crc checksum
|
||||
(poly=0x1021, init=0xFFFF, xorout=0x0000).</dd>
|
||||
<dt><code>%<ccitt16a></code></dt>
|
||||
<dd>Two bytes. The unusual (but <a target="ex"
|
||||
href="http://www.joegeluso.com/software/articles/ccitt.htm">correct?</a>)
|
||||
implementation of the CCITT standard 16 bit crc checksum with augment.
|
||||
(poly=0x1021, init=0x1D0F, xorout=0x0000).</dd>
|
||||
<dt><code>%<ccitt16x></code> or <code>%<crc16c></code> or <code>%<xmodem></code></dt>
|
||||
<dd>Two bytes. The XMODEM checksum.
|
||||
(poly=0x1021, init=0x0000, xorout=0x0000).</dd>
|
||||
<dt><code>%<crc32></code></dt>
|
||||
<dd>Four bytes. The standard 32 bit crc checksum.
|
||||
(poly=0x04C11DB7, init=0xFFFFFFFF, xorout=0xFFFFFFFF).</dd>
|
||||
<dt><code>%<crc32r></code></dt>
|
||||
<dd>Four bytes. The standard reflected 32 bit crc checksum.
|
||||
(poly=0x04C11DB7, init=0xFFFFFFFF, xorout=0xFFFFFFFF).</dd>
|
||||
<dt><code>%<jamcrc></code></dt>
|
||||
<dd>Four bytes. Another reflected 32 bit crc checksum.
|
||||
(poly=0x04C11DB7, init=0xFFFFFFFF, xorout=0x00000000).</dd>
|
||||
<dt><code>%<adler32></code></dt>
|
||||
<dd>Four bytes. The Adler32 checksum according to <a target="ex"
|
||||
href="http://www.ietf.org/rfc/rfc1950.txt">RFC 1950</a>.</dd>
|
||||
<dd>
|
||||
The bitwise inverse of the sum of all characters modulo 2<sup>8</sup>.
|
||||
<br>
|
||||
One byte. <code>123456789%<~sum8></code> = 0x22
|
||||
</dd>
|
||||
<dt><code>%<notsum16></code> or <code>%<~sum16></code></dt>
|
||||
<dd>
|
||||
The bitwise inverse of the sum of all characters modulo 2<sup>16</sup>.
|
||||
<br>
|
||||
Two bytes. <code>123456789%<~sum16></code> = 0xfe22
|
||||
</dd>
|
||||
<dt><code>%<notsum32></code> or <code>%<~sum32></code></dt>
|
||||
<dd>
|
||||
The bitwise inverse of the sum of all characters modulo 2<sup>32</sup>.
|
||||
<br>
|
||||
Four bytes. <code>123456789%<~sum32></code> = 0xfffffe22
|
||||
</dd>
|
||||
<dt><code>%<hexsum8></code></dt>
|
||||
<dd>One byte. The sum of all hex digits. (Other characters are ignored.)</dd>
|
||||
<dd>
|
||||
The sum of all hexadecimal digits. (Other characters are ignored.)
|
||||
<br>
|
||||
One byte. <code>123456789%<hexsum8></code> = 0x2d
|
||||
</dd>
|
||||
<dt><code>%<xor></code></dt>
|
||||
<dd>
|
||||
All characters xor'ed.
|
||||
<br>
|
||||
One byte. <code>123456789%<xor></code> = 0x31
|
||||
</dd>
|
||||
<dt><code>%<xor7></code></dt>
|
||||
<dd>
|
||||
All characters xor'ed modulo 2<sup>7</sup>.
|
||||
<br>
|
||||
One byte. <code>123456789%<xor7></code> = 0x31
|
||||
</dd>
|
||||
<dt><code>%<crc8></code></dt>
|
||||
<dd>
|
||||
An often used 8 bit crc checksum
|
||||
(poly=0x07, init=0x00, xorout=0x00).
|
||||
<br>
|
||||
One byte. <code>123456789%<crc8></code> = 0x31
|
||||
</dd>
|
||||
<dt><code>%<ccitt8></code></dt>
|
||||
<dd>
|
||||
The CCITT standard 8 bit crc checksum
|
||||
(poly=0x31, init=0x00, xorout=0x00).
|
||||
<br>
|
||||
One byte. <code>123456789%<ccitt8></code> = 0xf4
|
||||
</dd>
|
||||
<dt><code>%<crc16></code></dt>
|
||||
<dd>
|
||||
An often used 16 bit crc checksum
|
||||
(poly=0x8005, init=0x0000, xorout=0x0000).
|
||||
<br>
|
||||
Two bytes. <code>123456789%<crc16></code> = 0xfee8
|
||||
</dd>
|
||||
<dt><code>%<crc16r></code></dt>
|
||||
<dd>
|
||||
An often used reflected 16 bit crc checksum
|
||||
(poly=0x8005, init=0x0000, xorout=0x0000).
|
||||
<br>
|
||||
Two bytes. <code>123456789%<crc16r></code> = 0xbb3d
|
||||
</dd>
|
||||
<dt><code>%<ccitt16></code></dt>
|
||||
<dd>
|
||||
The usual (but <a target="ex"
|
||||
href="http://srecord.sourceforge.net/crc16-ccitt.html">wrong?</a>)
|
||||
implementation of the CCITT standard 16 bit crc checksum
|
||||
(poly=0x1021, init=0xFFFF, xorout=0x0000).
|
||||
<br>
|
||||
Two bytes. <code>123456789%<ccitt16></code> = 0x29b1
|
||||
</dd>
|
||||
<dt><code>%<ccitt16a></code></dt>
|
||||
<dd>
|
||||
The unusual (but <a target="ex"
|
||||
href="http://srecord.sourceforge.net/crc16-ccitt.html">correct?</a>)
|
||||
implementation of the CCITT standard 16 bit crc checksum with augment.
|
||||
(poly=0x1021, init=0x1D0F, xorout=0x0000).
|
||||
<br>
|
||||
Two bytes. <code>123456789%<ccitt16a></code> = 0xe5cc
|
||||
</dd>
|
||||
<dt><code>%<ccitt16x></code> or <code>%<crc16c></code> or <code>%<xmodem></code></dt>
|
||||
<dd>
|
||||
The XMODEM checksum.
|
||||
(poly=0x1021, init=0x0000, xorout=0x0000).
|
||||
<br>
|
||||
Two bytes. <code>123456789%<xmodem></code> = 0x31c3
|
||||
</dd>
|
||||
<dt><code>%<crc32></code></dt>
|
||||
<dd>
|
||||
The standard 32 bit crc checksum.
|
||||
(poly=0x04C11DB7, init=0xFFFFFFFF, xorout=0xFFFFFFFF).
|
||||
<br>
|
||||
Four bytes. <code>123456789%<crc32></code> = 0xfc891918
|
||||
</dd>
|
||||
<dt><code>%<crc32r></code></dt>
|
||||
<dd>
|
||||
The standard reflected 32 bit crc checksum.
|
||||
(poly=0x04C11DB7, init=0xFFFFFFFF, xorout=0xFFFFFFFF).
|
||||
<br>
|
||||
Four bytes. <code>123456789%<crc32r></code> = 0xcbf43926
|
||||
</dd>
|
||||
<dt><code>%<jamcrc></code></dt>
|
||||
<dd>
|
||||
Another reflected 32 bit crc checksum.
|
||||
(poly=0x04C11DB7, init=0xFFFFFFFF, xorout=0x00000000).
|
||||
<br>
|
||||
Four bytes. <code>123456789%<jamcrc></code> = 0x340bc6d9
|
||||
</dd>
|
||||
<dt><code>%<adler32></code></dt>
|
||||
<dd>
|
||||
The Adler32 checksum according to <a target="ex"
|
||||
href="http://www.ietf.org/rfc/rfc1950.txt">RFC 1950</a>.
|
||||
<br>
|
||||
Four bytes. <code>123456789%<adler32></code> = 0x091e01de
|
||||
</dd>
|
||||
</dl>
|
||||
|
||||
<a name="regex"></a>
|
||||
@ -584,7 +683,6 @@ Format flags <code>+</code>, <code>-</code>, and space are supported in
|
||||
the usual way (always sign, left justified, space instead of + sign).
|
||||
Flags <code>#</code> and <code>0</code> are unsupported.
|
||||
</p>
|
||||
<div class="new">
|
||||
<a name="timestamp"></a>
|
||||
<h2>14. Timestamp DOUBLE converter (<code>%T(<em>timeformat</em>)</code>)</h2>
|
||||
<p>
|
||||
@ -637,7 +735,6 @@ Because of the complexity of the problem, locales are not supported.
|
||||
Thus, only the English month names can be used (week day names are
|
||||
ignored anyway).
|
||||
</p>
|
||||
</div>
|
||||
<hr>
|
||||
<p align="right"><a href="processing.html">Next: Record Processing</a></p>
|
||||
<p><small>Dirk Zimoch, 2011</small></p>
|
||||
|
||||
@ -1479,6 +1479,7 @@ scanValue(const StreamFormat& fmt, long& value)
|
||||
}
|
||||
else return -1;
|
||||
}
|
||||
if (fmt.flags & fix_width_flag && consumed != fmt.width) return -1;
|
||||
if (consumed > inputLine.length()-consumedInput) return -1;
|
||||
debug("StreamCore::scanValue(%s) scanned %li\n",
|
||||
name(), value);
|
||||
@ -1510,6 +1511,7 @@ scanValue(const StreamFormat& fmt, double& value)
|
||||
}
|
||||
else return -1;
|
||||
}
|
||||
if (fmt.flags & fix_width_flag && (consumed != (fmt.width + fmt.prec + 1))) return -1;
|
||||
if (consumed > inputLine.length()-consumedInput) return -1;
|
||||
debug("StreamCore::scanValue(%s) scanned %#g\n",
|
||||
name(), value);
|
||||
@ -1542,6 +1544,7 @@ scanValue(const StreamFormat& fmt, char* value, long maxlen)
|
||||
}
|
||||
else return -1;
|
||||
}
|
||||
if (fmt.flags & fix_width_flag && consumed != fmt.width) return -1;
|
||||
if (consumed > inputLine.length()-consumedInput) return -1;
|
||||
#ifndef NO_TEMPORARY
|
||||
debug("StreamCore::scanValue(%s) scanned \"%s\"\n",
|
||||
|
||||
@ -30,7 +30,8 @@ typedef enum {
|
||||
zero_flag = 0x10,
|
||||
skip_flag = 0x20,
|
||||
default_flag = 0x40,
|
||||
compare_flag = 0x80
|
||||
compare_flag = 0x80,
|
||||
fix_width_flag = 0x100,
|
||||
} StreamFormatFlag;
|
||||
|
||||
typedef enum {
|
||||
@ -48,7 +49,7 @@ typedef struct StreamFormat
|
||||
{
|
||||
char conv;
|
||||
StreamFormatType type;
|
||||
unsigned char flags;
|
||||
unsigned short flags;
|
||||
short prec;
|
||||
unsigned short width;
|
||||
unsigned short infolen;
|
||||
|
||||
@ -38,7 +38,7 @@ parseFormat(const char*& source, FormatType formatType, StreamFormat& streamForm
|
||||
{
|
||||
/*
|
||||
source := [flags] [width] ['.' prec] conv [extra]
|
||||
flags := '-' | '+' | ' ' | '#' | '0' | '*' | '?' | '='
|
||||
flags := '-' | '+' | ' ' | '#' | '0' | '*' | '?' | '=' | '!'
|
||||
width := integer
|
||||
prec := integer
|
||||
conv := character
|
||||
@ -85,6 +85,15 @@ parseFormat(const char*& source, FormatType formatType, StreamFormat& streamForm
|
||||
}
|
||||
streamFormat.flags |= default_flag;
|
||||
break;
|
||||
case '!':
|
||||
if (formatType != ScanFormat)
|
||||
{
|
||||
error("Use of fixed width modifier '!' "
|
||||
"only allowed in input formats\n");
|
||||
return false;
|
||||
}
|
||||
streamFormat.flags |= fix_width_flag;
|
||||
break;
|
||||
case '=':
|
||||
if (formatType != ScanFormat)
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user