<?xml version="1.0"?>
<!-- $Revision: 5737 $ -->
<!-- a bflang2 file should start with a xml declaration -->
<!--
the root tag of the bflang2 file is <bflang name="NAME">
it should have attribute 'name', which is a human readable name of the
language that is defined
-->
<bflang name="Sample">
<!-- within the bflang tag is first a <header> and then a <definition> tag.
the header tag is parsed during bluefish startup.
the definition tag is parsed only on-demand. if a file of this type is opened -->
<header>
<!-- the <header> tag can have <mime> and <highlight> -->
<!-- <mime type="TYPE"> defines which mime-types are described by this language file.
There can be multiple mime tags in the header section (for example C source and
C header files have a different mimetype and can be described by the same
language file) -->
<mime type="fake/sample"/>
<!-- <highlight name="NAME" style="STYLE"> defines which element-types that are defined in
the file, and which styles should be applied for each of these types. So if an element
in this file has attribute highlight="foo", this section should have <highlight name="foo"
style="somestyle"/>. Look at other language files and try to re-use styles !!!!!!!!!
For the end-user it is convenient if styles are re-used. All languages that define a comment
should use style 'comment' by default.
-->
<highlight name="comment" style="comment" />
<!-- <option> defines an option that can be set for this language -->
<option name="allphpfunctions" default="1" description="All php functions" />
<!-- this example adds the option 'allphpfunctions' to the language file
if in the <definition> section of this file we have a <group class="allphpfunctions"> the user
can enable/disable this complete section with this option
-->
<!-- there are a couple of hardcoded option names for options that the user may set -->
<option name="load_reference" default="1" />
<!-- whether or not to load the reference data for this language -->
<option name="load_completion" default="1" />
<!-- whether or not to load the auto completion data for this language -->
<option name="autocomplete_tags" default="1" />
<!-- whether or not to close <tag> -->
</header>
<properties>
<!-- properties are parsed after the first file with this mime type has been loaded -->
<comment id="/**/" type="block" start="/*" end="*/" />
<comment id="//" type="line" start="//" />
<!-- the comment tag specifies which line and block comments that are possible for the smart comment function -->
<smartindent characters="{" />
<!-- smartindent characters specify which characters, followed by a return, should increase the indenting -->
<default_spellcheck enabled="1" />
<!-- default_spellcheck defines if regions that are not highlighted will be checked by the spell checker.
This is typically enabled for HTML/XML like languages, and disabled (or ignored, because the default=0)
for all programming languages
-->
</properties>
<definition>
<!-- within <definition> the actual language description is found. A language definition always
starts with a <context> tag, and contains ONE SINGLE context tag.
-->
<context symbols="><&; 	 ">
<!-- <context symbols="LIST OF CHARACTERS" highlight="HIGHLIGHT-TYPE" id="IDENTIFIER"
a <context> tag should always define "symbols". Symbols are those characters that may start or end an element.
To detect function strlen in the following examples (language C):
i=strlen(a);
i+strlen(a);
i*strlen (a);
we need at least symbols =+*(
In most languages all whitespace is a symbol ( =space, 	=tab, =newline, =carriange return).
In xml/sgml/html only '<>&;' are symbols, but withtin a tag also "' are symbols.
The optional attribute highlight may specify a highlight type that is valid for the complete text region
that has this context. Useful for 'comment' or 'string' type of contexts where the complete context is
highlighted
The optional attribute 'id' is used to define an identifier which can be used to re-use this context.
To re-use a context, use <context idref="IDENTIFIER" /> where IDENTIFIER refers to a previously defined
context. The file is parsed top to bottom.
Within <context> there can be <element> <tag> and <group> tags.
-->
<element pattern="while" highlight="keyword"/>
<!--
<element> defines an element that is highlighted, or can be autocompleted, or an element that starts a new context
it always needs attribute 'pattern' which defines the pattern that will be looked for in this context
the pattern can be defined in 'regular expression' style, to do this add attribute is_regex="1". however, there is
only limited regular expression support. you may use
- a range of characters such as [a-z0-9;']
- an inverted range such as [^0-9]
- operators such as ? (zero or one), + (one or more), and * (zero or more)
- subpatterns such as ab(fg)?
-->
<element pattern="'[^']*'" is_regex="1" highlight="string"/>
<!--
a pattern may be case insensitive, set case_insens="1"
to highlight the pattern use attribute highlight="TYPE", where TYPE should be defined within the <header>
section of the language file
<element> may have attribute 'id' so this element may be referred to later. To re-use element 'foo' later in the file
use <element idref="foo" />
-->
<!-- next is a block detection example -->
<element id="bracket{" pattern="{" starts_block="1" highlight="brackets" />
<element pattern="}" ends_block="1" blockstartelement="bracket{" highlight="brackets" />
<!--
an element may start or end a block. a block consists of two patterns (start and end) where the contents between
the start and the end may be hidden when the block is 'folded'.
to make a pattern a block start define starts_block="1" and use the 'id' attribute
to specify a pattern that ends a block use ends_block="1" and use blockstartelement="FOO" where FOO is the id of
the start-of-block-element
-->
<!-- next is an context example, a javascript comment -->
<element pattern="/*" highlight="c-style-comment">
<context symbols="*/	 " highlight="c-style-comment">
<element pattern="*/" highlight="c-style-comment" ends_context="1" />
</context>
</element>
<!--
an element may also start a new context for the scanner.
whenever this pattern is found the engine switches to this context
and starts scanning only the patterns defined in this context. To do this define <context></context>
between <element> and </element>. within this <context> there are entirely different patterns. There
can be only 1 context within an element.
There is an end of the context too in most languages. To make the scanner switch back to the previous context
an element INSIDE the inner context that has ends_context="NUM" where NUM specifies the number of contexts
that are ended by this element. Because
context may be nested there may be several contexts inside each other.
Basically context switches work like a stack. Lets take the example
------------
i = 1;
/* text */
i = 1 + 1;
------------
pattern '/*' exists in the initial context, but when it is found, the initial context is pushed on the
context stack, and the scanner switches to a new context context (for c-style-comment). In this context
there exists only a single pattern: '*/'
The scanner now continues until it finds */, at this point it pops 1 context from the stack, and thus in
this example it continues with the initial context
-->
<!-- next is a nested context example, inside a php comment, there may be the end of the php block. Note that
this element has ends_context=2 -->
<element pattern="<?php" highlight="php-block">
<context symbols="?*/+-=*&<>	 ">
<element pattern="?>" highlight="php-block" ends_context="1" />
<element pattern="/*" highlight="c-style-comment">
<context symbols="*/	 " highlight="c-style-comment">
<element pattern="*/" highlight="c-style-comment" ends_context="1" />
<element pattern="?>" highlight="php-block" ends_context="2" />
</context>
</element>
</context>
</element>
<!-- next example shows autocompletion options -->
<element pattern="while" highlight="keyword" autocomplete="1" autocomplete_append="() {" autocomplete_backup_cursor="3"/>
<!--
an pattern may also be autocompletable. to enable this use autocomplete="1"
often it is convenient if not only the pattern itself can be completed but some common
characters are appended. use autocomplete_append="STRING" to define any characters that
will be autocompleted. The cursor position AFTER auto completion can be set back a couple
of characters. This is defined by attribute autocomplete_backup_cursor
a regular expession pattern may be autocompletable as well. but to autocomplete the pattern
itself usually makes no sense because it matches various other patterns. use
autocomplete_string="STRING" to autocomplete STRING in this context -->
<!-- next example shows a xml/sgml tag with attributes -->
<tag name="body" highlight="tag" attributes="style,class,id" attribhighlight="attribute" />
<!--
because there are many languages that use sgml/xml/html style patterns there is <tag> for convenience.
it should have attribute 'name' to specify the name of the tag
the attribute 'attributes' defines attributes that are valid for this tag
to highlight the tag use highlight="TYPE" where TYPE is the highlight type defined in the <header> section
to highlight attributes use attrib_highlight="TYPE"
-->
<!-- next example show the equivalent of the above <tag. as you can see a single tag
needs a lot of configuration. That's why the convenience <tag was created. -->
<element id="<body" pattern="<body" highlight="tag" starts_block="1">
<context symbols=">\"=' 	 " >
<element pattern="style" highlight="attribute" />
<element pattern="class" highlight="attribute" />
<element pattern="id" highlight="attribute" />
<element id="__internal_tag_string_d__" pattern=""[^"]*"" is_regex="1" highlight="string" />
<element id="__internal_tag_string_s__" pattern="'[^']*'" is_regex="1" highlight="string" />
<element pattern="/>" ends_context="1" highlight="tag" />
</context>
</element>
<element pattern="</body<" highlight="tag" ends_block="1" blockstartelement="<body" />
<!--
a <tag> may also start a new context just as <element> does
-->
<!-- next example shows autocompletion for tags -->
<tag name="img" attributes="style,class,id,src,width,height"
autocomplete_append=">" attrib_autocomplete_append="=""" attrib_autocomplete_backup_cursor="2"/>
<!--
a <tag> automatically autocompletes. it also has a 'autocomplete_append' attribute, but
also an 'attrib_autocomplete_append' atribute.
-->
<!-- next example shows auto closing options for tags -->
<tag name="br" no_close="1" />
<!--
a <tag> will automaticaly autoclose (if not disabled for the complete language file).
some tags don't need a closing tag. use no_close="1"
-->
<!-- next example shows how to set SGML short tags -->
<tag name="img" sgml_shorttag="1" />
<!--
in XML or XHTML a tag always needs to be closed, either <img /> or <img></img>
in SGML <img> is also allowed. set sgml_shorttag="1" to enable this
-->
<group highlight="keyword" autocomplete="1">
<element pattern="for"/>
<element pattern="while"/>
</group>
<!--
often there are many elements that need the same attribute such as highlight or autocomplete
to make this easier you can group these elements inside <group>.
supported atributes are:
- highlight
- autocomplete
- autocomplete_append
- class
- case_insens
- is_regex
-->
<group attribhighlight="attribute" highlight="tag"
autocomplete_append=">" attrib_autocomplete_append="=""" >
<tag name="p" attributes="style,id,width"/>
<tag name="div" attributes="style,id" />
</group>
<!--
also many <tag> entries can have the same attributes, so these can also be
grouped inside <group>
supported attributes are:
- highlight
- attribhighlight
- autocomplete_append
- attrib_autocomplete_append
- class
-->
<!--
a special usage of <group is to allow the user to disable/enable a section of the file.
if the <header> section has <option name="allphpfunctions" default="1" description="All php functions" />
we can put this option into effect like this:
-->
<group class="allphpfunctions">
<element pattern="mysql_query" />
<element pattern="mysql_fetch_row" />
<element pattern="mysql_fetch_array" />
</group>
<!-- the reverse is also supported, using the notclass attribute, this can be used to make a
option that disables one section but enables a different section -->
<group notclass="mysetting">
<element pattern="foo" />
<group>
<group class="mysetting">
<element pattern="bar" />
<group>
<!-- -------- OPTIMISATIONS ---------
context re-use (<context idref=""/>) is more important than element or tag re-use
(<element idref=""/> or <tag idref=""/>).
element or tag re-use saves memory when the reference documentation is large,
and saves a few bytes when the same element/tag is used multiple times.
A re-used element is still compiled into every DFA table from every context it is
used in, and the DFA table uses most memory.
context re-use saves more bytes: although the contexts themlseves are tiny,
the same DFA table is re-used when a context is re-used (and the DFA table
is the largest memory object, easily 500 times larger than the elements).
As illustration here the sizes from html.bflang2
table 7906 (1976.50 Kbytes) --- the DFA tables, compiled patterns for each context
contexts 100 (4.69 Kbytes) --- context metadata
matches 1752 (123.19 Kbytes) --- element/tag metadata
-->
<!-- --------------------- END OF DOCUMENTATION ------------------------------------------------ -->
<element pattern="[0-9.]+" is_regex="1" highlight="value"/>
<element pattern="TRUE" autocomplete="1" highlight="value"/>
<element pattern="FALSE" autocomplete="1" highlight="value"/>
<element pattern="[" starts_block="1" mayfold="1" highlight="brackets" />
<element pattern="]" ends_block="1" blockstartelement="[" highlight="brackets" />
<element pattern="(" starts_block="1" mayfold="1" highlight="brackets" />
<element pattern=")" ends_block="1" blockstartelement="(" highlight="brackets" />
<element pattern=""" highlight="string">
<context symbols="\"" highlight="string">
<element pattern="\"" highlight="string" />
<element pattern=""" highlight="string" ends_context="1" />
</context>
</element>
<element pattern="'" highlight="string">
<context symbols="\'" highlight="string">
<element pattern="\'" highlight="string" />
<element pattern="'" highlight="string" ends_context="1" />
</context>
</element>
<element pattern="$[a-z0-9._]+" is_regex="1" case_insens="1" highlight="variable"/>
<element pattern="(//|#)" is_regex="1" highlight="php-comment">
<context symbols="?> " highlight="php-comment">
<element pattern=" " ends_context="1" />
<element pattern="?>" ends_context="2" ends_block="1" blockstartelement="<?php" highlight="php-tag" mayfold="1" />
</context>
</element>
<element pattern="?>" ends_block="1" blockstartelement="<?php" highlight="php-tag" mayfold="1" ends_context="1" />
<element pattern="<!--" highlight="html-comment" starts_block="1">
<context symbols="-> 	 " highlight="html-comment">
<element pattern="-->" ends_block="1" blockstartelement="<!--" highlight="html-comment" mayfold="1" ends_context="1" />
</context>
</element>
<element pattern="&[a-z0-9#]+;" is_regex="1" highlight="value" />
</context>
</definition>
</bflang>
