Text helper class. Provides simple methods for working with text.
Class declared in SYSPATH/classes/text.php on line 3.
array
$unitslink to thisnumber units and text equivalents
array(31) ( 1000000000 => string(7) "billion" 1000000 => string(7) "million" 1000 => string(8) "thousand" 100 => string(7) "hundred" 90 => string(6) "ninety" 80 => string(6) "eighty" 70 => string(7) "seventy" 60 => string(5) "sixty" 50 => string(5) "fifty" 40 => string(6) "fourty" 30 => string(6) "thirty" 20 => string(6) "twenty" 19 => string(8) "nineteen" 18 => string(8) "eighteen" 17 => string(9) "seventeen" 16 => string(7) "sixteen" 15 => string(7) "fifteen" 14 => string(8) "fourteen" 13 => string(8) "thirteen" 12 => string(6) "twelve" 11 => string(6) "eleven" 10 => string(3) "ten" 9 => string(4) "nine" 8 => string(5) "eight" 7 => string(5) "seven" 6 => string(3) "six" 5 => string(4) "five" 4 => string(4) "four" 3 => string(5) "three" 2 => string(3) "two" 1 => string(3) "one" )
Alternates between two or more strings.
echo
Text::alternate(
'one'
,
'two'
);
// "one"
echo
Text::alternate(
'one'
,
'two'
);
// "two"
echo
Text::alternate(
'one'
,
'two'
);
// "one"
Note that using multiple iterations of different strings may produce unexpected results.
string
public
static
function
alternate()
{
static
$i
;
if
(func_num_args() === 0)
{
$i
= 0;
return
''
;
}
$args
= func_get_args();
return
$args
[(
$i
++ %
count
(
$args
))];
}
Converts text email addresses and anchors into links. Existing links will not be altered.
echo
Text::auto_link(
$text
);
This method is not foolproof since it uses regex to parse HTML.
string
$text
required - Text to auto linkstring
public
static
function
auto_link(
$text
)
{
// Auto link emails first to prevent problems with "www.domain.com@example.com"
return
Text::auto_link_urls(Text::auto_link_emails(
$text
));
}
Converts text email addresses into links. Existing links will not be altered.
echo
Text::auto_link_emails(
$text
);
This method is not foolproof since it uses regex to parse HTML.
string
$text
required - Text to auto linkstring
public
static
function
auto_link_emails(
$text
)
{
// Find and replace all email addresses that are not part of an existing html mailto anchor
// Note: The "58;" negative lookbehind prevents matching of existing encoded html mailto anchors
// The html entity for a colon (:) is : or : or : etc.
return
preg_replace_callback(
'~\b(?<!href="mailto:|58;)(?!\.)[-+_a-z0-9.]++(?<!\.)@(?![-.])[-a-z0-9.]+(?<!\.)\.[a-z]{2,6}\b(?!</a>)~i'
,
'Text::_auto_link_emails_callback'
,
$text
);
}
Converts text anchors into links. Existing links will not be altered.
echo
Text::auto_link_urls(
$text
);
This method is not foolproof since it uses regex to parse HTML.
string
$text
required - Text to auto linkstring
public
static
function
auto_link_urls(
$text
)
{
// Find and replace all http/https/ftp/ftps links that are not part of an existing html anchor
$text
= preg_replace_callback(
'~\b(?<!href="|">)(?:ht|f)tps?://[^<\s]+(?:/|\b)~i'
,
'Text::_auto_link_urls_callback1'
,
$text
);
// Find and replace all naked www.links.com (without http://)
return
preg_replace_callback(
'~\b(?<!://|">)www(?:\.[a-z0-9][-a-z0-9]*+)+\.[a-z]{2,6}[^<\s]*\b~i'
,
'Text::_auto_link_urls_callback2'
,
$text
);
}
Automatically applies "p" and "br" markup to text. Basically nl2br on steroids.
echo
Text::auto_p(
$text
);
This method is not foolproof since it uses regex to parse HTML.
string
$str
required - Subjectboolean
$br
= bool TRUE - Convert single linebreaks to string
public
static
function
auto_p(
$str
,
$br
= TRUE)
{
// Trim whitespace
if
((
$str
= trim(
$str
)) ===
''
)
return
''
;
// Standardize newlines
$str
=
str_replace
(
array
(
"\r\n"
,
"\r"
),
"\n"
,
$str
);
// Trim whitespace on each line
$str
= preg_replace(
'~^[ \t]+~m'
,
''
,
$str
);
$str
= preg_replace(
'~[ \t]+$~m'
,
''
,
$str
);
// The following regexes only need to be executed if the string contains html
if
(
$html_found
= (
strpos
(
$str
,
'<'
) !== FALSE))
{
// Elements that should not be surrounded by p tags
$no_p
=
'(?:p|div|h[1-6r]|ul|ol|li|blockquote|d[dlt]|pre|t[dhr]|t(?:able|body|foot|head)|c(?:aption|olgroup)|form|s(?:elect|tyle)|a(?:ddress|rea)|ma(?:p|th))'
;
// Put at least two linebreaks before and after $no_p elements
$str
= preg_replace(
'~^<'
.
$no_p
.
'[^>]*+>~im'
,
"\n$0"
,
$str
);
$str
= preg_replace(
'~</'
.
$no_p
.
'\s*+>$~im'
,
"$0\n"
,
$str
);
}
// Do the <p> magic!
$str
=
'<p>'
.trim(
$str
).
'</p>'
;
$str
= preg_replace(
'~\n{2,}~'
,
"</p>\n\n<p>"
,
$str
);
// The following regexes only need to be executed if the string contains html
if
(
$html_found
!== FALSE)
{
// Remove p tags around $no_p elements
$str
= preg_replace(
'~<p>(?=</?'
.
$no_p
.
'[^>]*+>)~i'
,
''
,
$str
);
$str
= preg_replace(
'~(</?'
.
$no_p
.
'[^>]*+>)</p>~i'
,
'$1'
,
$str
);
}
// Convert single linebreaks to <br />
if
(
$br
=== TRUE)
{
$str
= preg_replace(
'~(?<!\n)\n(?!\n)~'
,
"<br />\n"
,
$str
);
}
return
$str
;
}
Returns human readable sizes. Based on original functions written by Aidan Lister and Quentin Zervaas.
echo
Text::bytes(
filesize
(
$file
));
integer
$bytes
required - Size in bytesstring
$force_unit
= NULL - A definitive unitstring
$format
= NULL - The return string formatboolean
$si
= bool TRUE - Whether to use SI prefixes or IECstring
public
static
function
bytes(
$bytes
,
$force_unit
= NULL,
$format
= NULL,
$si
= TRUE)
{
// Format string
$format
= (
$format
=== NULL) ?
'%01.2f %s'
: (string)
$format
;
// IEC prefixes (binary)
if
(
$si
== FALSE OR
strpos
(
$force_unit
,
'i'
) !== FALSE)
{
$units
=
array
(
'B'
,
'KiB'
,
'MiB'
,
'GiB'
,
'TiB'
,
'PiB'
);
$mod
= 1024;
}
// SI prefixes (decimal)
else
{
$units
=
array
(
'B'
,
'kB'
,
'MB'
,
'GB'
,
'TB'
,
'PB'
);
$mod
= 1000;
}
// Determine unit to use
if
((
$power
=
array_search
( (string)
$force_unit
,
$units
)) === FALSE)
{
$power
= (
$bytes
> 0) ?
floor
(log(
$bytes
,
$mod
)) : 0;
}
return
sprintf(
$format
,
$bytes
/ pow(
$mod
,
$power
),
$units
[
$power
]);
}
Replaces the given words with a string.
// Displays "What the #####, man!"
echo
Text::censor(
'What the frick, man!'
,
array
(
'frick'
=>
'#####'
,
));
string
$str
required - Phrase to replace words inarray
$badwords
required - Words to replacestring
$replacement
= string(1) "#" - Replacement stringboolean
$replace_partial_words
= bool TRUE - Replace words across word boundries (space, period, etc)string
public
static
function
censor(
$str
,
$badwords
,
$replacement
=
'#'
,
$replace_partial_words
= TRUE)
{
foreach
( (
array
)
$badwords
as
$key
=>
$badword
)
{
$badwords
[
$key
] =
str_replace
(
'\*'
,
'\S*?'
, preg_quote( (string)
$badword
));
}
$regex
=
'('
.implode(
'|'
,
$badwords
).
')'
;
if
(
$replace_partial_words
=== FALSE)
{
// Just using \b isn't sufficient when we need to replace a badword that already contains word boundaries itself
$regex
=
'(?<=\b|\s|^)'
.
$regex
.
'(?=\b|\s|$)'
;
}
$regex
=
'!'
.
$regex
.
'!ui'
;
if
(UTF8::
strlen
(
$replacement
) == 1)
{
$regex
.=
'e'
;
return
preg_replace(
$regex
,
'str_repeat($replacement, UTF8::strlen(\'$1\'))'
,
$str
);
}
return
preg_replace(
$regex
,
$replacement
,
$str
);
}
Limits a phrase to a given number of characters.
$text
= Text::limit_chars(
$text
);
string
$str
required - Phrase to limit characters ofinteger
$limit
= integer 100 - Number of characters to limit tostring
$end_char
= NULL - End character or entityboolean
$preserve_words
= bool FALSE - Enable or disable the preservation of words while limitingstring
public
static
function
limit_chars(
$str
,
$limit
= 100,
$end_char
= NULL,
$preserve_words
= FALSE)
{
$end_char
= (
$end_char
=== NULL) ?
'…'
:
$end_char
;
$limit
= (int)
$limit
;
if
(trim(
$str
) ===
''
OR UTF8::
strlen
(
$str
) <=
$limit
)
return
$str
;
if
(
$limit
<= 0)
return
$end_char
;
if
(
$preserve_words
=== FALSE)
return
rtrim(UTF8::
substr
(
$str
, 0,
$limit
)).
$end_char
;
// Don't preserve words. The limit is considered the top limit.
// No strings with a length longer than $limit should be returned.
if
( ! preg_match(
'/^.{0,'
.
$limit
.
'}\s/us'
,
$str
,
$matches
))
return
$end_char
;
return
rtrim(
$matches
[0]).((
strlen
(
$matches
[0]) ===
strlen
(
$str
)) ?
''
:
$end_char
);
}
Limits a phrase to a given number of words.
$text
= Text::limit_words(
$text
);
string
$str
required - Phrase to limit words ofinteger
$limit
= integer 100 - Number of words to limit tostring
$end_char
= NULL - End character or entitystring
public
static
function
limit_words(
$str
,
$limit
= 100,
$end_char
= NULL)
{
$limit
= (int)
$limit
;
$end_char
= (
$end_char
=== NULL) ?
'…'
:
$end_char
;
if
(trim(
$str
) ===
''
)
return
$str
;
if
(
$limit
<= 0)
return
$end_char
;
preg_match(
'/^\s*+(?:\S++\s*+){1,'
.
$limit
.
'}/u'
,
$str
,
$matches
);
// Only attach the end character if the matched string is shorter
// than the starting string.
return
rtrim(
$matches
[0]).((
strlen
(
$matches
[0]) ===
strlen
(
$str
)) ?
''
:
$end_char
);
}
Format a number to human-readable text.
// Display: one thousand and twenty-four
echo
Text::number(1024);
// Display: five million, six hundred and thirty-two
echo
Text::number(5000632);
integer
$number
required - Number to formatstring
public
static
function
number(
$number
)
{
// The number must always be an integer
$number
= (int)
$number
;
// Uncompiled text version
$text
=
array
();
// Last matched unit within the loop
$last_unit
= NULL;
// The last matched item within the loop
$last_item
=
''
;
foreach
(Text::
$units
as
$unit
=>
$name
)
{
if
(
$number
/
$unit
>= 1)
{
// $value = the number of times the number is divisble by unit
$number
-=
$unit
* (
$value
= (int)
floor
(
$number
/
$unit
));
// Temporary var for textifying the current unit
$item
=
''
;
if
(
$unit
< 100)
{
if
(
$last_unit
< 100 AND
$last_unit
>= 20)
{
$last_item
.=
'-'
.
$name
;
}
else
{
$item
=
$name
;
}
}
else
{
$item
= Text::number(
$value
).
' '
.
$name
;
}
// In the situation that we need to make a composite number (i.e. twenty-three)
// then we need to modify the previous entry
if
(
empty
(
$item
))
{
array_pop
(
$text
);
$item
=
$last_item
;
}
$last_item
=
$text
[] =
$item
;
$last_unit
=
$unit
;
}
}
if
(
count
(
$text
) > 1)
{
$and
=
array_pop
(
$text
);
}
$text
= implode(
', '
,
$text
);
if
(isset(
$and
))
{
$text
.=
' and '
.
$and
;
}
return
$text
;
}
Generates a random string of a given type and length.
$str
= Text::random();
// 8 character random string
The following types are supported:
You can also create a custom type by providing the "pool" of characters as the type.
string
$type
= NULL - A type of pool, or a string of characters to use as the poolinteger
$length
= integer 8 - Length of string to returnstring
public
static
function
random(
$type
= NULL,
$length
= 8)
{
if
(
$type
=== NULL)
{
// Default is to generate an alphanumeric string
$type
=
'alnum'
;
}
$utf8
= FALSE;
switch
(
$type
)
{
case
'alnum'
:
$pool
=
'0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ'
;
break
;
case
'alpha'
:
$pool
=
'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ'
;
break
;
case
'hexdec'
:
$pool
=
'0123456789abcdef'
;
break
;
case
'numeric'
:
$pool
=
'0123456789'
;
break
;
case
'nozero'
:
$pool
=
'123456789'
;
break
;
case
'distinct'
:
$pool
=
'2345679ACDEFHJKLMNPRSTUVWXYZ'
;
break
;
default
:
$pool
= (string)
$type
;
$utf8
= ! UTF8::is_ascii(
$pool
);
break
;
}
// Split the pool into an array of characters
$pool
= (
$utf8
=== TRUE) ? UTF8::
str_split
(
$pool
, 1) :
str_split
(
$pool
, 1);
// Largest pool key
$max
=
count
(
$pool
) - 1;
$str
=
''
;
for
(
$i
= 0;
$i
<
$length
;
$i
++)
{
// Select a random character from the pool and add it to the string
$str
.=
$pool
[mt_rand(0,
$max
)];
}
// Make sure alnum strings contain at least one letter and one digit
if
(
$type
===
'alnum'
AND
$length
> 1)
{
if
(ctype_alpha(
$str
))
{
// Add a random digit
$str
[mt_rand(0,
$length
- 1)] =
chr
(mt_rand(48, 57));
}
elseif
(ctype_digit(
$str
))
{
// Add a random letter
$str
[mt_rand(0,
$length
- 1)] =
chr
(mt_rand(65, 90));
}
}
return
$str
;
}
Reduces multiple slashes in a string to single slashes.
$str
= Text::reduce_slashes(
'foo//bar/baz'
); //
"foo/bar/baz"
string
$str
required - String to reduce slashes ofstring
public
static
function
reduce_slashes(
$str
)
{
return
preg_replace(
'#(?<!:)//+#'
,
'/'
,
$str
);
}
Finds the text that is similar between a set of words.
$match
= Text::similar(
array
(
'fred'
,
'fran'
,
'free'
);
// "fr"
array
$words
required - Words to find similar text ofstring
public
static
function
similar(
array
$words
)
{
// First word is the word to match against
$word
= current(
$words
);
for
(
$i
= 0,
$max
=
strlen
(
$word
);
$i
<
$max
; ++
$i
)
{
foreach
(
$words
as
$w
)
{
// Once a difference is found, break out of the loops
if
( ! isset(
$w
[
$i
]) OR
$w
[
$i
] !==
$word
[
$i
])
break
2;
}
}
// Return the similar text
return
substr
(
$word
, 0,
$i
);
}
Uppercase words that are not separated by spaces, using a custom delimiter or the default.
$str
= Text::ucfirst(
'content-type'
);
// returns "Content-Type"
string
$string
required - String to transformstring
$delimiter
= string(1) "-" - Delemiter to usestring
public
static
function
ucfirst(
$string
,
$delimiter
=
'-'
)
{
// Put the keys back the Case-Convention expected
return
implode(
$delimiter
,
array_map
(
'ucfirst'
,
explode
(
$delimiter
,
$string
)));
}
Prevents widow words by inserting a non-breaking space between the last two words.
echo
Text::widont(
$text
);
string
$str
required - Text to remove widows fromstring
public
static
function
widont(
$str
)
{
$str
= rtrim(
$str
);
$space
=
strrpos
(
$str
,
' '
);
if
(
$space
!== FALSE)
{
$str
=
substr
(
$str
, 0,
$space
).
' '
.
substr
(
$str
,
$space
+ 1);
}
return
$str
;
}
protected
static
function
_auto_link_emails_callback(
$matches
)
{
return
HTML::mailto(
$matches
[0]);
}
protected
static
function
_auto_link_urls_callback1(
$matches
)
{
return
HTML::anchor(
$matches
[0]);
}
protected
static
function
_auto_link_urls_callback2(
$matches
)
{
}