Difference between revisions of "Module:String"

From annadreambrush.com/wiki
Jump to navigation Jump to search
imported>Dragons flight
(add support for finding the position of a string or pattern inside another string.)
imported>Dragons flight
(Update to allow for unnamed parameters. This is necessary because some string function need to preserve leading / trailing whitespace in order to work properly.)
Line 27: Line 27:
  
 
Returns the first index in "source" that is a match to "target".  Indexing is 1-based,
 
Returns the first index in "source" that is a match to "target".  Indexing is 1-based,
and the function returns -1 if the "target" string is not present in "source".  Both
+
and the function returns -1 if the "target" string is not present in "source".
strings have any leading or trailing whitespace removed before searching.
 
  
 
Important Note: If the "target" string is empty / missing, this function returns a
 
Important Note: If the "target" string is empty / missing, this function returns a
Line 35: Line 34:
 
]====]
 
]====]
 
function str.str_find( frame )
 
function str.str_find( frame )
     local source_str = frame.args.source or '';
+
     local new_args = str._getParameters( frame.args, {'source', 'target'} );
     local target_str = frame.args.target or '';
+
    local source_str = new_args['source'] or '';
    if target_str == '' then
+
     local target_str = new_args['target'] or '';
 +
 
 +
if target_str == '' then
 
         return 1;
 
         return 1;
 
     end     
 
     end     
Line 55: Line 56:
 
string.
 
string.
  
Parameters:
+
Usage:
 +
{{#invoke:String|find|source_str|target_string|start_index|plain_flag}}
 +
OR
 +
{{#invoke:String|find|source=source_str|target=target_str|start=start_index|plain=plain_flag}}
 +
 
 +
Parameters
 
     source: The string to search
 
     source: The string to search
 
     target: The string or pattern to find within source
 
     target: The string or pattern to find within source
Line 61: Line 67:
 
     plain: Boolean flag indicating that target should be understood as plain
 
     plain: Boolean flag indicating that target should be understood as plain
 
         text and not as a Lua style regular expression, defaults to true
 
         text and not as a Lua style regular expression, defaults to true
       
+
 
 +
If invoked using named parameters, Mediawiki will automatically remove any leading or
 +
trailing whitespace from the parameter.  In some circumstances this is desirable, in
 +
other cases one may want to preserve the whitespace.
 +
 
 
This function returns the first index >= "start" where "target" can be found  
 
This function returns the first index >= "start" where "target" can be found  
 
within "source".  Indices are 1-based.  If "target" is not found, then this  
 
within "source".  Indices are 1-based.  If "target" is not found, then this  
Line 67: Line 77:
 
function also returns 0.
 
function also returns 0.
  
Both "source" and "target" will be trimmed so that any leading or trailing
+
This function should be safe for UTF-8 strings.
whitespace is removed prior to searching.  This function should be safe for
 
UTF-8 strings.
 
 
]====]
 
]====]
 
function str.find( frame )
 
function str.find( frame )
     local source_str = frame.args.source or '';
+
     local new_args = str._getParameters( frame.args, {'source', 'target', 'start', 'plain' } );
     local pattern = frame.args.target or '';
+
    local source_str = new_args['source'] or '';
     local start_pos = tonumber(frame.args.start) or 1;
+
     local pattern = new_args['target'] or '';
     local plain = frame.args.plain or true;
+
     local start_pos = tonumber(new_args['start']) or 1;
 +
     local plain = new_args['plain'] or true;
 
          
 
          
 
     if source_str == '' or pattern == '' then
 
     if source_str == '' or pattern == '' then
Line 97: Line 106:
 
     return start
 
     return start
 
end
 
end
 +
 +
--[====[
 +
Helper function that populates the argument list given that user may need to use a mix of
 +
named and unnamed parameters.  This is relevant because named parameters are not
 +
identical to unnamed parameters due to string trimming, and when dealing with strings
 +
we sometimes want to either preserve or remove that whitespace depending on the application.
 +
]====]
 +
function str._getParameters( frame_args, arg_list )
 +
    local new_args = {};
 +
    local index = 1;
 +
    local value;
 +
   
 +
    for i,arg in ipairs( arg_list ) do
 +
        value = frame_args[arg]
 +
        if value == nil then
 +
            value = frame_args[index];
 +
            index = index + 1;
 +
        end
 +
        new_args[arg] = value;
 +
    end
 +
   
 +
    return new_args;
 +
end       
 +
 
return str
 
return str

Revision as of 19:56, 22 February 2013

Documentation for this module may be created at Module:String/doc

local str = {}

function str.len( frame )
    return mw.ustring.len( frame.args.s )
end

function str.sub( frame )
    return mw.ustring.sub( frame.args.s, tonumber( frame.args.i ), tonumber( frame.args.j ) )
end

function str.sublength( frame )
    local i = tonumber( frame.args.i ) or 0
    local len = tonumber( frame.args.len )
    return mw.ustring.sub( frame.args.s, i + 1, len and ( i + len ) )
end

function str.match( frame )
    return mw.ustring.match( frame.args.s, frame.args.pattern, tonumber( frame.args.i ) )
end

--[====[
str_find

This function duplicates the behavior of {{str_find}}, including all of its quirks.
This is provided in order to support existing templates, but is NOT RECOMMENDED for 
new code and templates.  New code is recommended to use the "find" function instead.

Returns the first index in "source" that is a match to "target".  Indexing is 1-based,
and the function returns -1 if the "target" string is not present in "source".

Important Note: If the "target" string is empty / missing, this function returns a
value of "1", which is generally unexpected behavior, and must be accounted for
separatetly.
]====]
function str.str_find( frame )
    local new_args = str._getParameters( frame.args, {'source', 'target'} );
    local source_str = new_args['source'] or '';
    local target_str = new_args['target'] or '';

if target_str == '' then
        return 1;
    end    
    
    local start = mw.ustring.find( source_str, target_str, 1, true )
    if start == nil then
        start = -1
    end
    
    return start
end

--[====[
find

This function allows one to search for a target string or pattern within another
string.

Usage:
{{#invoke:String|find|source_str|target_string|start_index|plain_flag}}
OR
{{#invoke:String|find|source=source_str|target=target_str|start=start_index|plain=plain_flag}}

Parameters
    source: The string to search
    target: The string or pattern to find within source
    start: The index within the source string to start the search, defaults to 1
    plain: Boolean flag indicating that target should be understood as plain
        text and not as a Lua style regular expression, defaults to true

If invoked using named parameters, Mediawiki will automatically remove any leading or
trailing whitespace from the parameter.  In some circumstances this is desirable, in 
other cases one may want to preserve the whitespace.

This function returns the first index >= "start" where "target" can be found 
within "source".  Indices are 1-based.  If "target" is not found, then this 
function returns 0.  If either "source" or "target" are missing / empty, this
function also returns 0.

This function should be safe for UTF-8 strings.
]====]
function str.find( frame )
    local new_args = str._getParameters( frame.args, {'source', 'target', 'start', 'plain' } ); 
    local source_str = new_args['source'] or '';
    local pattern = new_args['target'] or '';
    local start_pos = tonumber(new_args['start']) or 1;
    local plain = new_args['plain'] or true;
        
    if source_str == '' or pattern == '' then
        return 0;
    end    
    
    if type( plain ) == 'string' then
        plain = plain:lower();
        if plain == 'false' or plain == 'no' or plain == '0' then
            plain = false;
        else
            plain = true;
        end    
    end

    local start = mw.ustring.find( source_str, pattern, start_pos, plain )
    if start == nil then
        start = 0
    end
    
    return start
end

--[====[
Helper function that populates the argument list given that user may need to use a mix of
named and unnamed parameters.  This is relevant because named parameters are not
identical to unnamed parameters due to string trimming, and when dealing with strings
we sometimes want to either preserve or remove that whitespace depending on the application.
]====]
function str._getParameters( frame_args, arg_list )
    local new_args = {};
    local index = 1;
    local value;
    
    for i,arg in ipairs( arg_list ) do
        value = frame_args[arg]
        if value == nil then
            value = frame_args[index];
            index = index + 1;
        end
        new_args[arg] = value;
    end
    
    return new_args;
end        

return str