Difference between revisions of "Module:String"

From WPRDC Wiki
Jump to navigation Jump to search
>Dragons flight
(add description and whitespace handling option for len)
>Dragons flight
(improves commenting, adds whitespace and error handling to sub, improvements to error handling generally.)
Line 1: Line 1:
--[[ 
This module is intended to provide access to basic string functions.
Most of the functions provided here can be invoked with named parameters,
unnamed parameters, or a mixture.  If named parameters are used, Mediawiki will
automatically remove any leading or trailing whitespace from the parameter. 
Depending on the intended use, it may be advantageous to either preserve or
remove such whitespace.
Global options
    ignore_errors: If set to 'true' or 1, any error condition will result in
        an empty string being returned rather than an error message. 
       
    error_category: If an error occurs, specifies the name of a category to
        include with the error message.  The default category is 
        [Category:Errors reported by Module String].  If set to an empty
        string, no category will be added during an error.   
]]
local str = {}
local str = {}


--[====[
--[[
len
len


Line 9: Line 29:
{{#invoke:String|len|target_string|}}
{{#invoke:String|len|target_string|}}
OR
OR
{{#invoke:String|pos|s=target_string}}
{{#invoke:String|len|s=target_string}}


Parameters
Parameters
Line 16: Line 36:
If invoked using named parameters, Mediawiki will automatically remove any leading or
If invoked using named parameters, Mediawiki will automatically remove any leading or
trailing whitespace from the target string.   
trailing whitespace from the target string.   
]====]
]]
function str.len( frame )
function str.len( frame )
     local new_args = str._getParameters( frame.args, {'s'} );
     local new_args = str._getParameters( frame.args, {'s'} );
Line 23: Line 43:
end
end


--[[
sub
This function returns a substring of the target string at specified indices.
Usage:
{{#invoke:String|sub|target_string|start_index|end_index}}
OR
{{#invoke:String|sub|s=target_string|i=start_index|j=end_index}}
Parameters
    s: The string to return a subset of
    i: The fist index of the substring to return, defaults to 1.
    j: The last index of the string to return, defaults to the last character.
   
The first character of the string is assigned an index of 1.  If either i or j
is a negative value, it is interpreted the same as selecting a character by
counting from the end of the string.  Hence, a value of -1 is the same as
selecting the last character of the string.
If the requested indices are out of range for the given string, an error is
reported.
]]
function str.sub( frame )
function str.sub( frame )
     return mw.ustring.sub( frame.args.s, tonumber( frame.args.i ), tonumber( frame.args.j ) )
     local new_args = str._getParameters( frame.args, { 's', 'i', 'j' } );
    local s = new_args['s'] or '';
    local i = tonumber( new_args['i'] ) or 1;
    local j = tonumber( new_args['j'] ) or -1;
   
    local len = mw.ustring.len( s );
 
    -- Convert negatives for range checking
    if i < 0 then
        i = len + i + 1;
    end
    if j < 0 then
        j = len + j + 1;
    end
    if j < i then
        return str._error( 'String subset indices out of order' );
    end
   
    if i > len or j > len or i < 1 or j < 1 then
        return str._error( 'String subset index out of range' );
    end
   
    return mw.ustring.sub( s, i, j )
end
end


Line 37: Line 102:
end
end


--[====[
--[[
pos
pos


Line 61: Line 126:


A requested value of zero, or a value greater than the length of the string returns an error.
A requested value of zero, or a value greater than the length of the string returns an error.
]====]
]]
function str.pos( frame )
function str.pos( frame )
     local new_args = str._getParameters( frame.args, {'target', 'pos'} );
     local new_args = str._getParameters( frame.args, {'target', 'pos'} );
Line 68: Line 133:


     if pos == 0 or math.abs(pos) > mw.ustring.len( target_str ) then
     if pos == 0 or math.abs(pos) > mw.ustring.len( target_str ) then
         return '<strong class="error">String index out of range</strong>';
         return str._error( 'String index out of range' );
     end     
     end     
      
      
Line 74: Line 139:
end
end


--[====[
--[[
str_find
str_find


Line 87: Line 152:
value of "1", which is generally unexpected behavior, and must be accounted for
value of "1", which is generally unexpected behavior, and must be accounted for
separatetly.
separatetly.
]====]
]]
function str.str_find( frame )
function str.str_find( frame )
     local new_args = str._getParameters( frame.args, {'source', 'target'} );
     local new_args = str._getParameters( frame.args, {'source', 'target'} );
Line 105: Line 170:
end
end


--[====[
--[[
find
find


Line 133: Line 198:


This function should be safe for UTF-8 strings.
This function should be safe for UTF-8 strings.
]====]
]]
function str.find( frame )
function str.find( frame )
     local new_args = str._getParameters( frame.args, {'source', 'target', 'start', 'plain' } );  
     local new_args = str._getParameters( frame.args, {'source', 'target', 'start', 'plain' } );  
Line 155: Line 220:
end
end


--[====[
--[[
replace
replace


Line 174: Line 239:
     plain: Boolean flag indicating that pattern should be understood as plain
     plain: Boolean flag indicating that pattern 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  
]====]
]]
function str.replace( frame )
function str.replace( frame )
     local new_args = str._getParameters( frame.args, {'source', 'pattern', 'replace', 'count', 'plain' } );  
     local new_args = str._getParameters( frame.args, {'source', 'pattern', 'replace', 'count', 'plain' } );  
Line 204: Line 269:
end
end


--[====[
--[[
Helper function that populates the argument list given that user may need to use a mix of
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
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
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.
we sometimes want to either preserve or remove that whitespace depending on the application.
]====]
]]
function str._getParameters( frame_args, arg_list )
function str._getParameters( frame_args, arg_list )
     local new_args = {};
     local new_args = {};
Line 227: Line 292:
end         
end         


--[====[
--[[
Helper function to handle error messages.
]]
function str._error( error_str )
    local frame = mw.getCurrentFrame();
    local error_category = frame.args.error_category or 'Errors reported by Module String';
    local ignore_errors = frame.args.ignore_errors or false;
   
    if str._getBoolean(ignore_errors) then
        return '';
    end
   
    local error_str = '<strong class="error">String Module Error: ' .. error_str .. '</strong>';
    if error_category ~= '' then
        error_str = '[[Category:' .. error_category .. ']]' .. error_str;
    end       
   
    return error_str;
end
 
--[[
Helper Function to interpret boolean strings
Helper Function to interpret boolean strings
]====]
]]
function str._getBoolean( boolean_str )
function str._getBoolean( boolean_str )
     local boolean_value;
     local boolean_value;
Line 248: Line 333:
end
end


--[====[
--[[
Helper function that escapes all pattern characters so that they will be treated  
Helper function that escapes all pattern characters so that they will be treated  
as plain text.
as plain text.
]====]
]]
function str._escapePattern( pattern_str )
function str._escapePattern( pattern_str )
     return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" );
     return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" );

Revision as of 02:06, 25 February 2013

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

--[[  

This module is intended to provide access to basic string functions.

Most of the functions provided here can be invoked with named parameters, 
unnamed parameters, or a mixture.  If named parameters are used, Mediawiki will 
automatically remove any leading or trailing whitespace from the parameter.  
Depending on the intended use, it may be advantageous to either preserve or
remove such whitespace.

Global options
    ignore_errors: If set to 'true' or 1, any error condition will result in 
        an empty string being returned rather than an error message.  
        
    error_category: If an error occurs, specifies the name of a category to 
        include with the error message.  The default category is  
        [Category:Errors reported by Module String].  If set to an empty
        string, no category will be added during an error.    
]]

local str = {}

--[[
len

This function returns the length of the target string.

Usage:
{{#invoke:String|len|target_string|}}
OR
{{#invoke:String|len|s=target_string}}

Parameters
    s: The string whose length to report

If invoked using named parameters, Mediawiki will automatically remove any leading or
trailing whitespace from the target string.  
]]
function str.len( frame )
    local new_args = str._getParameters( frame.args, {'s'} );
    local s = new_args['s'] or '';
    return mw.ustring.len( s )
end

--[[
sub

This function returns a substring of the target string at specified indices.

Usage:
{{#invoke:String|sub|target_string|start_index|end_index}}
OR
{{#invoke:String|sub|s=target_string|i=start_index|j=end_index}}

Parameters
    s: The string to return a subset of
    i: The fist index of the substring to return, defaults to 1.
    j: The last index of the string to return, defaults to the last character.
    
The first character of the string is assigned an index of 1.  If either i or j
is a negative value, it is interpreted the same as selecting a character by 
counting from the end of the string.  Hence, a value of -1 is the same as 
selecting the last character of the string.

If the requested indices are out of range for the given string, an error is 
reported.
]]
function str.sub( frame )
    local new_args = str._getParameters( frame.args, { 's', 'i', 'j' } );
    local s = new_args['s'] or '';
    local i = tonumber( new_args['i'] ) or 1;
    local j = tonumber( new_args['j'] ) or -1;
    
    local len = mw.ustring.len( s );

    -- Convert negatives for range checking
    if i < 0 then
        i = len + i + 1;
    end
    if j < 0 then
        j = len + j + 1;
    end
    if j < i then
        return str._error( 'String subset indices out of order' );
    end
    
    if i > len or j > len or i < 1 or j < 1 then
        return str._error( 'String subset index out of range' );
    end
    
    return mw.ustring.sub( s, i, 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

--[[
pos

This function returns a single character from the target string at position pos.

Usage:
{{#invoke:String|pos|target_string|index_value}}
OR
{{#invoke:String|pos|target=target_string|pos=index_value}}

Parameters
    target: The string to search
    pos: The index for the character to return

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

The first character has an index value of 1.

If one requests a negative value, this function will select a character by counting backwards 
from the end of the string.  In other words pos = -1 is the same as asking for the last character.

A requested value of zero, or a value greater than the length of the string returns an error.
]]
function str.pos( frame )
    local new_args = str._getParameters( frame.args, {'target', 'pos'} );
    local target_str = new_args['target'] or '';
    local pos = tonumber( new_args['pos'] ) or 0;

    if pos == 0 or math.abs(pos) > mw.ustring.len( target_str ) then
        return str._error( 'String index out of range' );
    end    
    
    return mw.ustring.sub( target_str, pos, pos );
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    
    
    plain = str._getBoolean( plain );

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

--[[
replace

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

Usage:
{{#invoke:String|replace|source_str|pattern_string|replace_string|replacement_count|plain_flag}}
OR
{{#invoke:String|replace|source=source_string|pattern=pattern_string|replace=replace_string|
   count=replacement_count|plain=plain_flag}}

Parameters
    source: The string to search
    pattern: The string or pattern to find within source
    replace: The replacement text
    count: The number of occurences to replace, defaults to all.
    plain: Boolean flag indicating that pattern should be understood as plain
        text and not as a Lua style regular expression, defaults to true 
]]
function str.replace( frame )
    local new_args = str._getParameters( frame.args, {'source', 'pattern', 'replace', 'count', 'plain' } ); 
    local source_str = new_args['source'] or '';
    local pattern = new_args['pattern'] or '';
    local replace = new_args['replace'] or '';
    local count = tonumber( new_args['count'] );
    local plain = new_args['plain'] or true;
        
    if source_str == '' or pattern == '' then
        return source_str;
    end    
    plain = str._getBoolean( plain );

    if plain then
        pattern = str._escapePattern( pattern );
        replace = str._escapePattern( replace );
    end
    
    local result;

    if count ~= nil then
        result = mw.ustring.gsub( source_str, pattern, replace, count );
    else
        result = mw.ustring.gsub( source_str, pattern, replace );
    end        

    return result;
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        

--[[
Helper function to handle error messages.
]]
function str._error( error_str )
    local frame = mw.getCurrentFrame();
    local error_category = frame.args.error_category or 'Errors reported by Module String';
    local ignore_errors = frame.args.ignore_errors or false;
    
    if str._getBoolean(ignore_errors) then
        return '';
    end
    
    local error_str = '<strong class="error">String Module Error: ' .. error_str .. '</strong>';
    if error_category ~= '' then
        error_str = '[[Category:' .. error_category .. ']]' .. error_str;
    end        
    
    return error_str;
end

--[[
Helper Function to interpret boolean strings
]]
function str._getBoolean( boolean_str )
    local boolean_value;
    
    if type( boolean_str ) == 'string' then
        boolean_str = boolean_str:lower();
        if boolean_str == 'false' or boolean_str == 'no' or boolean_str == '0' then
            boolean_value = false;
        else
            boolean_value = true;
        end    
    elseif type( boolean_str ) == 'boolean' then
        boolean_value = boolean_str;
    else
        error( 'No boolean value found' );
    end    
    return boolean_value
end

--[[
Helper function that escapes all pattern characters so that they will be treated 
as plain text.
]]
function str._escapePattern( pattern_str )
    return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" );
end

return str