Module:String

 --[[

 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].

  no_category: If set to 'true' or 1, no category will be added if an error
  is generated.

 Unit tests for this module are available at Module:String/tests.
 ]]

 localstr={}

 --[[
 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.
 ]]
 functionstr.len(frame)
 localnew_args=str._getParameters(frame.args,{'s'});
 locals=new_args['s']or'';
 returnmw.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.
 ]]
 functionstr.sub(frame)
 localnew_args=str._getParameters(frame.args,{'s','i','j'});
 locals=new_args['s']or'';
 locali=tonumber(new_args['i'])or1;
 localj=tonumber(new_args['j'])or-1;

 locallen=mw.ustring.len(s);

 -- Convert negatives for range checking
 ifi<0then
 i=len+i+1;
 end
 ifj<0then
 j=len+j+1;
 end

 ifi>lenorj>lenori<1orj<1then
 returnstr._error('String subset index out of range');
 end
 ifj<ithen
 returnstr._error('String subset indices out of order');
 end

 returnmw.ustring.sub(s,i,j)
 end

 --[[
 This function implements that features of {{str sub old}} and is kept in order
 to maintain these older templates.
 ]]
 functionstr.sublength(frame)
 locali=tonumber(frame.args.i)or0
 locallen=tonumber(frame.args.len)
 returnmw.ustring.sub(frame.args.s,i+1,lenand(i+len))
 end

 --[[
 match

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

 Usage:
 {{#invoke:String|match|source_string|pattern_string|start_index|match_number|plain_flag|nomatch}}
 OR
 {{#invoke:String|pos|s=source_string|pattern=pattern_string|start=start_index
  |match=match_number|plain=plain_flag|nomatch=nomatch_output}}

 Parameters
  s: The string to search
  pattern: The pattern or string to find within the string
  start: The index within the source string to start the search. The first
  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
  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
  counting from the last match. Hence match = -1 is the same as requesting
  the last match. Defaults to 1.
  plain: A flag indicating that the pattern should be understood as plain
  text. Defaults to false.
  nomatch: If no match is found, output the "nomatch" value rather than an error.

 If invoked using named parameters, Mediawiki will automatically remove any leading or
 trailing whitespace from each string. In some circumstances this is desirable, in
 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
 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
 an empty string will be returned on any failure.

 For information on constructing Lua patterns, a form of [regular expression], see:

 * https://www.lua.org/manual/5.1/manual.html#5.4.1
 * https://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Patterns
 * https://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Ustring_patterns

 ]]
 -- This sub-routine is exported for use in other modules
 functionstr._match(s,pattern,start,match_index,plain,nomatch)
 ifs==''then
 returnstr._error('Target string is empty');
 end
 ifpattern==''then
 returnstr._error('Pattern string is empty');
 end
 start=tonumber(start)or1
 ifmath.abs(start)<1ormath.abs(start)>mw.ustring.len(s)then
 returnstr._error('Requested start is out of range');
 end
 ifmatch_index==0then
 returnstr._error('Match index is out of range');
 end
 ifplain_flagthen
 pattern=str._escapePattern(pattern);
 end

 localresult
 ifmatch_index==1then
 -- Find first match is simple case
 result=mw.ustring.match(s,pattern,start)
 else
 ifstart>1then
 s=mw.ustring.sub(s,start);
 end

 localiterator=mw.ustring.gmatch(s,pattern);
 ifmatch_index>0then
 -- Forward search
 forwiniteratordo
 match_index=match_index-1;
 ifmatch_index==0then
 result=w;
 break;
 end
 end
 else
 -- Reverse search
 localresult_table={};
 localcount=1;
 forwiniteratordo
 result_table[count]=w;
 count=count+1;
 end

 result=result_table[count+match_index];
 end
 end

 ifresult==nilthen
 ifnomatch==nilthen
 returnstr._error('Match not found');
 else
 returnnomatch;
 end
 else
 returnresult;
 end
 end
 -- This is the entry point for #invoke:String|match
 functionstr.match(frame)
 localnew_args=str._getParameters(frame.args,{'s','pattern','start','match','plain','nomatch'});
 locals=new_args['s']or'';
 localstart=tonumber(new_args['start'])or1;
 localplain_flag=str._getBoolean(new_args['plain']orfalse);
 localpattern=new_args['pattern']or'';
 localmatch_index=math.floor(tonumber(new_args['match'])or1);
 localnomatch=new_args['nomatch'];

 returnstr._match(s,pattern,start,match_index,plain,nomatch)
 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.
 ]]
 functionstr.pos(frame)
 localnew_args=str._getParameters(frame.args,{'target','pos'});
 localtarget_str=new_args['target']or'';
 localpos=tonumber(new_args['pos'])or0;

 ifpos==0ormath.abs(pos)>mw.ustring.len(target_str)then
 returnstr._error('String index out of range');
 end

 returnmw.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.
 ]]
 functionstr.str_find(frame)
 localnew_args=str._getParameters(frame.args,{'source','target'});
 localsource_str=new_args['source']or'';
 localtarget_str=new_args['target']or'';

 iftarget_str==''then
 return1;
 end

 localstart=mw.ustring.find(source_str,target_str,1,true)
 ifstart==nilthen
 start=-1
 end

 returnstart
 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.
 ]]
 functionstr.find(frame)
 localnew_args=str._getParameters(frame.args,{'source','target','start','plain'});
 localsource_str=new_args['source']or'';
 localpattern=new_args['target']or'';
 localstart_pos=tonumber(new_args['start'])or1;
 localplain=new_args['plain']ortrue;

 ifsource_str==''orpattern==''then
 return0;
 end

 plain=str._getBoolean(plain);

 localstart=mw.ustring.find(source_str,pattern,start_pos,plain)
 ifstart==nilthen
 start=0
 end

 returnstart
 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
 ]]
 functionstr.replace(frame)
 localnew_args=str._getParameters(frame.args,{'source','pattern','replace','count','plain'});
 localsource_str=new_args['source']or'';
 localpattern=new_args['pattern']or'';
 localreplace=new_args['replace']or'';
 localcount=tonumber(new_args['count']);
 localplain=new_args['plain']ortrue;

 ifsource_str==''orpattern==''then
 returnsource_str;
 end
 plain=str._getBoolean(plain);

 ifplainthen
 pattern=str._escapePattern(pattern);
 replace=mw.ustring.gsub(replace,"%%","%%%%");--Only need to escape replacement sequences.
 end

 localresult;

 ifcount~=nilthen
 result=mw.ustring.gsub(source_str,pattern,replace,count);
 else
 result=mw.ustring.gsub(source_str,pattern,replace);
 end

 returnresult;
 end

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

 functionstr.rep(frame)
 localrepetitions=tonumber(frame.args[2])
 ifnotrepetitionsthen
 returnstr._error('function rep expects a number as second parameter, received "'..(frame.args[2]or'')..'"')
 end
 returnstring.rep(frame.args[1]or'',repetitions)
 end

 --[[
 escapePattern

 This function escapes special characters from a Lua string pattern. See [1]
 for details on how patterns work.

 [1] https://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Patterns

 Usage:
 {{#invoke:String|escapePattern|pattern_string}}

 Parameters
  pattern_string: The pattern string to escape.
 ]]
 functionstr.escapePattern(frame)
 localpattern_str=frame.args[1]
 ifnotpattern_strthen
 returnstr._error('No pattern string specified');
 end
 localresult=str._escapePattern(pattern_str)
 returnresult
 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.
 ]]
 functionstr._getParameters(frame_args,arg_list)
 localnew_args={};
 localindex=1;
 localvalue;

 fori,arginipairs(arg_list)do
 value=frame_args[arg]
 ifvalue==nilthen
 value=frame_args[index];
 index=index+1;
 end
 new_args[arg]=value;
 end

 returnnew_args;
 end

 --[[
 Helper function to handle error messages.
 ]]
 functionstr._error(error_str)
 localframe=mw.getCurrentFrame();
 localerror_category=frame.args.error_categoryor'Errors reported by Module String';
 localignore_errors=frame.args.ignore_errorsorfalse;
 localno_category=frame.args.no_categoryorfalse;

 ifstr._getBoolean(ignore_errors)then
 return'';
 end

 localerror_str='<strong class="error">String Module Error: '..error_str..'</strong>';
 iferror_category~=''andnotstr._getBoolean(no_category)then
 error_str='[[Category:'..error_category..']]'..error_str;
 end

 returnerror_str;
 end

 --[[
 Helper Function to interpret boolean strings
 ]]
 functionstr._getBoolean(boolean_str)
 localboolean_value;

 iftype(boolean_str)=='string'then
 boolean_str=boolean_str:lower();
 ifboolean_str=='false'orboolean_str=='no'orboolean_str=='0'
 orboolean_str==''then
 boolean_value=false;
 else
 boolean_value=true;
 end
 elseiftype(boolean_str)=='boolean'then
 boolean_value=boolean_str;
 else
 error('No boolean value found');
 end
 returnboolean_value
 end

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

 returnstr