Module:String: Difference between revisions

1,120 bytes removed ,  5 years ago
m
use tabs instead of spaces, and remove trailing whitespace
(add an escapePattern function for escaping Lua patterns)
m (use tabs instead of spaces, and remove trailing whitespace)
Line 1: Line 1:
--[[
--[[


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


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


Global options
Global options
     ignore_errors: If set to 'true' or 1, any error condition will result in  
     ignore_errors: If set to 'true' or 1, any error condition will result in
         an empty string being returned rather than an error message.
         an empty string being returned rather than an error message.
       
 
     error_category: If an error occurs, specifies the name of a category to  
     error_category: If an error occurs, specifies the name of a category to
         include with the error message.  The default category is
         include with the error message.  The default category is
         [Category:Errors reported by Module String].
         [Category:Errors reported by Module String].
       
 
     no_category: If set to 'true' or 1, no category will be added if an error
     no_category: If set to 'true' or 1, no category will be added if an error
         is generated.
         is generated.
       
 
Unit tests for this module are available at Module:String/tests.
Unit tests for this module are available at Module:String/tests.
]]
]]
Line 39: Line 39:


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'} );
    local s = new_args['s'] or '';
local s = new_args['s'] or '';
    return mw.ustring.len( s )
return mw.ustring.len( s )
end
end


Line 61: Line 61:
     i: The fist index of the substring to return, defaults to 1.
     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.
     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
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  
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  
counting from the end of the string.  Hence, a value of -1 is the same as
selecting the last character of the string.
selecting the last character of the string.


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


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


Line 101: Line 101:
]]
]]
function str.sublength( frame )
function str.sublength( frame )
    local i = tonumber( frame.args.i ) or 0
local i = tonumber( frame.args.i ) or 0
    local len = tonumber( frame.args.len )
local len = tonumber( frame.args.len )
    return mw.ustring.sub( frame.args.s, i + 1, len and ( i + len ) )
return mw.ustring.sub( frame.args.s, i + 1, len and ( i + len ) )
end
end


Line 109: Line 109:
match
match


This function returns a substring from the source string that matches a  
This function returns a substring from the source string that matches a
specified pattern.
specified pattern.


Line 123: Line 123:
     start: The index within the source string to start the search.  The first
     start: The index within the source string to start the search.  The first
         character of the string has index 1.  Defaults to 1.
         character of the string has index 1.  Defaults to 1.
     match: In some cases it may be possible to make multiple matches on a single  
     match: In some cases it may be possible to make multiple matches on a single
         string.  This specifies which match to return, where the first match is  
         string.  This specifies which match to return, where the first match is
         match= 1.  If a negative number is specified then a match is returned  
         match= 1.  If a negative number is specified then a match is returned
         counting from the last match.  Hence match = -1 is the same as requesting
         counting from the last match.  Hence match = -1 is the same as requesting
         the last match.  Defaults to 1.
         the last match.  Defaults to 1.
Line 133: Line 133:


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 each string.  In some circumstances this is desirable, in  
trailing whitespace from each string.  In some circumstances this is desirable, in
other cases one may want to preserve the whitespace.
other cases one may want to preserve the whitespace.


If the match_number or start_index are out of range for the string being queried, then
If the match_number or start_index are out of range for the string being queried, then
this function generates an error.  An error is also generated if no match is found.
this function generates an error.  An error is also generated if no match is found.
If one adds the parameter ignore_errors=true, then the error will be suppressed and  
If one adds the parameter ignore_errors=true, then the error will be suppressed and
an empty string will be returned on any failure.
an empty string will be returned on any failure.


Line 149: Line 149:
]]
]]
function str.match( frame )
function str.match( frame )
    local new_args = str._getParameters( frame.args, {'s', 'pattern', 'start', 'match', 'plain', 'nomatch'} );
local new_args = str._getParameters( frame.args, {'s', 'pattern', 'start', 'match', 'plain', 'nomatch'} );
    local s = new_args['s'] or '';
local s = new_args['s'] or '';
    local start = tonumber( new_args['start'] ) or 1;
local start = tonumber( new_args['start'] ) or 1;
    local plain_flag = str._getBoolean( new_args['plain'] or false );
local plain_flag = str._getBoolean( new_args['plain'] or false );
    local pattern = new_args['pattern'] or '';
local pattern = new_args['pattern'] or '';
    local match_index = math.floor( tonumber(new_args['match']) or 1 );
local match_index = math.floor( tonumber(new_args['match']) or 1 );
    local nomatch = new_args['nomatch'];
local nomatch = new_args['nomatch'];
   
 
    if s == '' then
if s == '' then
        return str._error( 'Target string is empty' );
return str._error( 'Target string is empty' );
    end
end
    if pattern == '' then
if pattern == '' then
        return str._error( 'Pattern string is empty' );
return str._error( 'Pattern string is empty' );
    end
end
    if math.abs(start) < 1 or math.abs(start) > mw.ustring.len( s ) then
if math.abs(start) < 1 or math.abs(start) > mw.ustring.len( s ) then
        return str._error( 'Requested start is out of range' );
return str._error( 'Requested start is out of range' );
    end
end
    if match_index == 0 then
if match_index == 0 then
        return str._error( 'Match index is out of range' );
return str._error( 'Match index is out of range' );
    end
end
    if plain_flag then
if plain_flag then
        pattern = str._escapePattern( pattern );
pattern = str._escapePattern( pattern );
    end
end
   
 
    local result
local result
    if match_index == 1 then
if match_index == 1 then
        -- Find first match is simple case
-- Find first match is simple case
        result = mw.ustring.match( s, pattern, start )
result = mw.ustring.match( s, pattern, start )
    else
else
        if start > 1 then
if start > 1 then
            s = mw.ustring.sub( s, start );
s = mw.ustring.sub( s, start );
        end
end
       
 
        local iterator = mw.ustring.gmatch(s, pattern);
local iterator = mw.ustring.gmatch(s, pattern);
        if match_index > 0 then
if match_index > 0 then
            -- Forward search
-- Forward search
            for w in iterator do
for w in iterator do
                match_index = match_index - 1;
match_index = match_index - 1;
                if match_index == 0 then
if match_index == 0 then
                    result = w;
result = w;
                    break;
break;
                end
end
            end  
end
        else
else
            -- Reverse search
-- Reverse search
            local result_table = {};
local result_table = {};
            local count = 1;
local count = 1;
            for w in iterator do
for w in iterator do
                result_table[count] = w;
result_table[count] = w;
                count = count + 1;
count = count + 1;
            end
end
           
 
            result = result_table[ count + match_index ];          
result = result_table[ count + match_index ];
        end
end
    end      
end
   
 
    if result == nil then
if result == nil then
        if nomatch == nil then
if nomatch == nil then
            return str._error( 'Match not found' );
return str._error( 'Match not found' );
        else
else
            return nomatch;
return nomatch;
        end
end
    else
else
        return result;
return result;
    end
end
end
end


Line 231: Line 231:


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.  In some circumstances this is desirable, in  
trailing whitespace from the target string.  In some circumstances this is desirable, in
other cases one may want to preserve the whitespace.
other cases one may want to preserve the whitespace.


The first character has an index value of 1.
The first character has an index value of 1.


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


Line 242: Line 242:
]]
]]
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'} );
    local target_str = new_args['target'] or '';
local target_str = new_args['target'] or '';
    local pos = tonumber( new_args['pos'] ) or 0;
local pos = tonumber( new_args['pos'] ) or 0;


    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 str._error( 'String index out of range' );
return str._error( 'String index out of range' );
    end  
end
   
 
    return mw.ustring.sub( target_str, pos, pos );
return mw.ustring.sub( target_str, pos, pos );
end
end


Line 257: Line 257:


This function duplicates the behavior of {{str_find}}, including all of its quirks.
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  
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.
new code and templates.  New code is recommended to use the "find" function instead.


Line 268: Line 268:
]]
]]
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'} );
    local source_str = new_args['source'] or '';
local source_str = new_args['source'] or '';
    local target_str = new_args['target'] 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


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


Line 303: Line 303:


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 parameter.  In some circumstances this is desirable, in  
trailing whitespace from the parameter.  In some circumstances this is desirable, in
other cases one may want to preserve the whitespace.
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
function returns 0.  If either "source" or "target" are missing / empty, this
function returns 0.  If either "source" or "target" are missing / empty, this
function also returns 0.
function also returns 0.
Line 314: Line 314:
]]
]]
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' } );
    local source_str = new_args['source'] or '';
local source_str = new_args['source'] or '';
    local pattern = new_args['target'] or '';
local pattern = new_args['target'] or '';
    local start_pos = tonumber(new_args['start']) or 1;
local start_pos = tonumber(new_args['start']) or 1;
    local plain = new_args['plain'] or true;
local plain = new_args['plain'] or true;
       
 
    if source_str == '' or pattern == '' then
if source_str == '' or pattern == '' then
        return 0;
return 0;
    end  
end
   
 
    plain = str._getBoolean( plain );
plain = str._getBoolean( plain );
 
local start = mw.ustring.find( source_str, pattern, start_pos, plain )
if start == nil then
start = 0
end


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


Line 352: Line 352:
     count: The number of occurences to replace, defaults to all.
     count: The number of occurences to replace, defaults to all.
     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' } );
    local source_str = new_args['source'] or '';
local source_str = new_args['source'] or '';
    local pattern = new_args['pattern'] or '';
local pattern = new_args['pattern'] or '';
    local replace = new_args['replace'] or '';
local replace = new_args['replace'] or '';
    local count = tonumber( new_args['count'] );
local count = tonumber( new_args['count'] );
    local plain = new_args['plain'] or true;
local plain = new_args['plain'] or true;
       
 
    if source_str == '' or pattern == '' then
if source_str == '' or pattern == '' then
        return source_str;
return source_str;
    end  
end
    plain = str._getBoolean( plain );
plain = str._getBoolean( plain );
 
if plain then
pattern = str._escapePattern( pattern );
replace = mw.ustring.gsub( replace, "%%", "%%%%" ); --Only need to escape replacement sequences.
end


    if plain then
local result;
        pattern = str._escapePattern( pattern );
        replace = mw.ustring.gsub( replace, "%%", "%%%%" ); --Only need to escape replacement sequences.
    end
   
    local result;


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


    return result;
return result;
end
end


--[[  
--[[
     simple function to pipe string.rep to templates.
     simple function to pipe string.rep to templates.
]]
]]


function str.rep( frame )
function str.rep( frame )
    local repetitions = tonumber( frame.args[2] )
local repetitions = tonumber( frame.args[2] )
    if not repetitions then  
if not repetitions then
        return str._error( 'function rep expects a number as second parameter, received "' .. ( frame.args[2] or '' ) .. '"' )
return str._error( 'function rep expects a number as second parameter, received "' .. ( frame.args[2] or '' ) .. '"' )
    end
end
    return string.rep( frame.args[1] or '', repetitions )
return string.rep( frame.args[1] or '', repetitions )
end
end


Line 410: Line 410:
]]
]]
function str.escapePattern( frame )
function str.escapePattern( frame )
    local pattern_str = frame.args[1]
local pattern_str = frame.args[1]
    if not pattern_str then
if not pattern_str then
        return str._error( 'No pattern string specified' );
return str._error( 'No pattern string specified' );
    end
end
    local result = str._escapePattern( pattern_str )
local result = str._escapePattern( pattern_str )
    return result
return result
end
end


Line 425: Line 425:
]]
]]
function str._getParameters( frame_args, arg_list )
function str._getParameters( frame_args, arg_list )
    local new_args = {};
local new_args = {};
    local index = 1;
local index = 1;
    local value;
local value;
   
 
    for i,arg in ipairs( arg_list ) do
for i,arg in ipairs( arg_list ) do
        value = frame_args[arg]
value = frame_args[arg]
        if value == nil then
if value == nil then
            value = frame_args[index];
value = frame_args[index];
            index = index + 1;
index = index + 1;
        end
end
        new_args[arg] = value;
new_args[arg] = value;
    end
end
   
 
    return new_args;
return new_args;
end      
end


--[[
--[[
Line 445: Line 445:
]]
]]
function str._error( error_str )
function str._error( error_str )
    local frame = mw.getCurrentFrame();
local frame = mw.getCurrentFrame();
    local error_category = frame.args.error_category or 'Errors reported by Module String';
local error_category = frame.args.error_category or 'Errors reported by Module String';
    local ignore_errors = frame.args.ignore_errors or false;
local ignore_errors = frame.args.ignore_errors or false;
    local no_category = frame.args.no_category or false;
local no_category = frame.args.no_category or false;
   
 
    if str._getBoolean(ignore_errors) then
if str._getBoolean(ignore_errors) then
        return '';
return '';
    end
end
   
 
    local error_str = '<strong class="error">String Module Error: ' .. error_str .. '</strong>';
local error_str = '<strong class="error">String Module Error: ' .. error_str .. '</strong>';
    if error_category ~= '' and not str._getBoolean( no_category ) then
if error_category ~= '' and not str._getBoolean( no_category ) then
        error_str = '[[Category:' .. error_category .. ']]' .. error_str;
error_str = '[[Category:' .. error_category .. ']]' .. error_str;
    end      
end
   
 
    return error_str;
return error_str;
end
end


Line 466: Line 466:
]]
]]
function str._getBoolean( boolean_str )
function str._getBoolean( boolean_str )
    local boolean_value;
local boolean_value;
   
 
    if type( boolean_str ) == 'string' then
if type( boolean_str ) == 'string' then
        boolean_str = boolean_str:lower();
boolean_str = boolean_str:lower();
        if boolean_str == 'false' or boolean_str == 'no' or boolean_str == '0'  
if boolean_str == 'false' or boolean_str == 'no' or boolean_str == '0'
                or boolean_str == '' then
or boolean_str == '' then
            boolean_value = false;
boolean_value = false;
        else
else
            boolean_value = true;
boolean_value = true;
        end  
end
    elseif type( boolean_str ) == 'boolean' then
elseif type( boolean_str ) == 'boolean' then
        boolean_value = boolean_str;
boolean_value = boolean_str;
    else
else
        error( 'No boolean value found' );
error( 'No boolean value found' );
    end  
end
    return boolean_value
return boolean_value
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" );
end
end


return str
return str